Deep neural network (DNN) based speech recognizers have recently replaced Gaussian mixture (GMM) based systems as the state-of-the-art. HMM/DNN systems have kept many refinements of the HMM/GMM framework, even though some of these may be suboptimal for them. One such example is the creation of context-dependent tied states, for which an efficient decision tree state tying method exists. The tied states used to train DNNs are usually obtained using the same tying algorithm, even though it is based on likelihoods of Gaussians. In this paper, we investigate an alternative state clustering method that uses the Kullback-Leibler (KL) divergence of DNN output vectors to build the decision tree. It has already been successfully applied within the framework of KL-HMM systems, and here we show that it is also beneficial for HMM/DNN hybrids. In a large vocabulary recognition task we report a 4% relative word error rate reduction using this state clustering method.

Automatic speech recognition from distant microphones is a difficult task because recordings are affected by reverberation and background noise. First, the application of the deep neural network (DNN)/hidden Markov model (HMM) hybrid acoustic models for distant speech recognition task using AMI meeting corpus is investigated. This paper then proposes a feature transformation for removing reverberation and background noise artefacts from bottleneck features using DNN trained to learn the mapping between distant-talking speech features and close-talking speech bottleneck features. Experimental results on AMI meeting corpus reveal that the mismatch between close-talking and distant-talking conditions is largely reduced, with about 16% relative improvement over conventional bottleneck system (trained on close-talking speech). If the feature mapping is applied to close-talking speech, a minor degradation of 4% relative is observed.

Manual transcription of audio databases for automatic speech recognition (ASR) training is a costly and time-consuming process. State-of-the-art hybrid ASR systems that are based on deep neural networks (DNN) can exploit un-transcribed foreign data during unsupervised DNN pre-training or semi-supervised DNN training. We investigate the relevance of foreign data characteristics, in particular domain and language. Using three different datasets of the MediaParl and Ester databases, our experiments suggest that domain and language are equally important. Foreign data recorded under matched conditions (language and domain) yields the most improvement. The resulting ASR system yields about 5% relative improvement compared to the baseline system only trained on transcribed data. Our studies also reveal that the amount of foreign data used for semi-supervised training can be significantly reduced without degrading the ASR performance if confidence measure based data selection is employed.

This paper presents a study on multilingual deep neural network (DNN) based acoustic modeling and its application to new languages. We investigate the effect of phone merging on multilingual DNN in context of rapid language adaptation. Moreover, the combination of multilingual DNNs with Kullback-Leibler divergence based acoustic modeling (KL-HMM) is explored. Using ten different languages from the Globalphone database, our studies reveal that crosslingual acoustic model transfer through multilingual DNNs is superior to unsupervised RBM pre-training and greedy layer-wise supervised training. We also found that KL-HMM based decoding consistently outperforms conventional hybrid decoding, especially in low-resource scenarios. Furthermore, the experiments indicate that multilingual DNN training equally benefits from simple phoneset concatenation and manually derived universal phonesets.

Posterior features have been shown to yield very good performance in multiple contexts including speech recognition, spoken term detection, and template matching. These days, posterior features are usually estimated at the output of a neural network. More recently, sparse representation has also been shown to potentially provide additional advantages to improve discrimination and robustness. One possible instance of this, is referred to as exemplar-based sparse representation. The present work investigates how to exploit sparse modelling together with posterior space properties to further improve speech recognition features. In that context, we leverage exemplar-based sparse representation, and propose a novel approach to project phone posterior features into a new, high-dimensional, sparse feature space. In fact, exploiting the properties of posterior spaces, we generate, new, high-dimensional, linguistically inspired (sub-phone and words), posterior distributions. Validation experiments are performed on the Phonebook (isolated words) and HIWIRE (continuous speech) databases, which support the effectiveness of the proposed approach for speech recognition tasks.

Walliserdeutsch is a Swiss German dialect spoken in the south west of Switzerland. To investigate the potential of automatic speech processing of Walliserdeutsch, a small database was collected based mainly on broadcast news from a local radio station. Experiments suggest that automatic speech recognition is feasible: use of another (Swiss German) database shows that the small data size lends itself to bootstrapping from other data; use of Kullback-Leibler HMM suggests that phoneme mapping techniques can compensate for a grapheme-based dictionary. Experiments also indicate that statistical machine translation is feasible; the difficulty of small data size is offset by the close proximity to (high) German.

The development of an Automatic Speech Recognition (ASR) system for the bilingual MediaParl corpus is challenging for several reasons: (1) reverberant recordings, (2) accented speech, and (3) no prior information about the language. In that context, we employ frequency domain linear prediction-based (FDLP) features to reduce the effect of reverberation, exploit bilingual deep neural networks applied in Tandem and hybrid acoustic modeling approaches to significantly improve ASR for accented speech and develop a fully bilingual ASR system using entropy-based decoding-graph selection. Our experiments indicate that the proposed bilingual ASR system performs similar to a language-specific ASR system if approximately five seconds of speech are available.

Posterior based acoustic modeling techniques such as Kullback-Leibler divergence based HMM (KL-HMM) and Tandem are able to exploit out-of-language data through posterior features, estimated by a Multi-Layer Perceptron (MLP). In this paper, we investigate the performance of posterior based approaches in the context of under-resourced speech recognition when a standard three-layer MLP is replaced by a deeper five-layer MLP. The deeper MLP architecture yields similar gains of about 15% (relative) for Tandem, KL-HMM as well as for a hybrid HMM/MLP system that directly uses the posterior estimates as emission probabilities. The best performing system, a bilingual KL-HMM based on a deep MLP, jointly trained on Afrikaans and Dutch data, performs 13% better than a hybrid system using the same bilingual MLP and 26% better than a subspace Gaussian mixture system only trained on Afrikaans data.

Kullback-Leibler divergence based hidden Markov models (KL-HMM) have recently been introduced as an efficient and principled way to directly model sequences of posterior vectors to perform Automatic Speech Recognition (ASR). Through efficient feature level adaptation and parsimonious use of parameters, KL-HMM was successfully applied to accented and under-resourced speech recognition tasks. In this paper, inspired from Maximum A Posteriori (MAP) adaptation, we further boost KL-HMM performance by applying Bayesian speaker adaptation, directly applied to posterior features. This approach performs a simple, adaptive regression between phone posteriors estimated with a Multilayer Perceptron (MLP) on large amounts of speaker-independent training data, and speaker-specific phone posteriors generated by the speaker-independent MLP on very limited amount of speaker-specific adaptation data. Using Swiss French data (MediaParl), we show that such speaker adaptive KL-HMM can significantly outperform conventional adaptation techniques on non-native speech while yielding similar performance on native data.

Recent studies have shown that speech recognizers may benefit from data in languages other than the target language through efficient acoustic model- or feature-level adaptation. Crosslingual Tandem-Subspace Gaussian Mixture Models (SGMM) are successfully able to combine acoustic model- and feature-level adaptation techniques. More specifically, we focus on under-resourced languages (Afrikaans in our case) and perform feature-level adaptation through the estimation of phone class posterior features with a Multilayer Perceptron that was trained on data from a similar language with large amounts of available speech data (Dutch in our case). The same Dutch data can also be exploited on an acoustic model-level by training globally-shared SGMM parameters in a crosslingual way. The two adaptation techniques are indeed complementary and result in a crosslingual Tandem-SGMM system that yields relative improvement of about 22% compared to a standard speech recognizer on an Afrikaans phoneme recognition task. Interestingly, eventual score-level combination of the individual SGMM systems yields additional 3% relative improvement.

In the context of hybrid HMM/MLP Automatic Speech Recognition (ASR), this paper describes an investigation into a new type of stochastic phone space transformation, which maps “source” phone (or phone HMM state) posterior probabilities (as obtained at the output of a Multilayer Perceptron/MLP) into “destination” phone (HMM phone state) posterior probabilities. The resulting stochastic matrix transformation can be used within the same language to automatically adapt to different phone formats (e.g., IPA) or across languages. Additionally, as shown here, it can also be applied successfully to non-native speech recognition. In the same spirit as MLLR adaptation, or MLP adaptation, the approach proposed here is directly mapping posterior distributions, and is trained by optimizing on a small amount of adaptation data a Kullback-Leibler based cost function, along a modified version of an iterative EM algorithm. On a non-native English database (HIWIRE), and comparing with multiple setups (monophone and triphone mapping, MLLR adaptation) we show that the resulting posterior mapping yields state-of-the-art results using very limited amounts of adaptation data in mono-, cross- and multi-lingual setups. We also show that “universal” phone posteriors, trained on a large amount of multilingual data, can be transformed to English phone posteriors, resulting in an ASR system that significantly outperforms a system trained on English data only. Finally, we demonstrate that the proposed approach outperforms alternative data-driven, as well as a knowledge-based, mapping techniques.

Setting out from the point of view that automatic speech recognition (ASR) ought to benefit from data in languages other than the target language, we propose a novel Kullback-Leibler (KL) divergence based method that is able to exploit multilingual information in the form of universal phoneme posterior probabilities conditioned on the acoustics. We formulate a means to train a recognizer on several different languages, and subsequently recognize speech in a target language for which only a small amount of data is available. Taking the Greek SpeechDat(II) data as an example, we show that the proposed formulation is sound, and show that it is able to out-perform a current state-of-the-art HMM/GMM system. We also use a hybrid Tandem-like system to further understand the source of the benefit.

In this paper we revisit the recently proposed triphone mapping as an alternative to decision tree state clustering. We generalize triphone mapping to Kullback-Leibler based hidden Markov models for acoustic modeling and propose a modified training procedure for the Gaussian mixture model based acoustic modeling. We compare the triphone mapping to decision tree state clustering on the Wall Street Journal task as well as in the context of an under-resourced language by using Greek data from the SpeechDat(II) corpus. Experiments reveal that triphone mapping has the best overall performance and is robust against varying the acoustic modeling technique as well as variable amounts of training data.

In this paper, we explore how different acoustic modeling techniques can benefit from data in languages other than the target language. We propose an algorithm to perform decision tree state clustering for the recently proposed Kullback-Leibler divergence based hidden Markov models (KL-HMM) and compare it to subspace Gaussian mixture modeling (SGMM). KL-HMM can exploit multilingual information in the form of universal phoneme posterior features and SGMM benefits from a universal background model that can be trained on multilingual data. Taking the Greek SpeechDat(II) data as an example, we show that KL-HMM performs best for small amounts of target language data.

MediaParl is a Swiss accented bilingual database containing recordings in both French and German as they are spoken in Switzerland. The data were recorded at the Valais Parliament. Valais is a bilingual Swiss canton with many local accents and dialects. Therefore, the database contains data with high variability and is suitable to study multilingual, accented and non-native speech recognition as well as language identification and language switch detection. We also define monolingual and mixed language automatic speech recognition and language identification tasks and evaluate baseline systems. The database is publicly available for download.

The speaker diarization system developed at the International Computer Science Institute (ICSI) has played a prominent role in the speaker diarization community, and many researchers in the rich transcription community have adopted methods and techniques developed for the ICSI speaker diarization engine. Although there have been many related publications over the years, previous articles only presented changes and improvements rather than a description of the full system. Attempting to replicate the ICSI speaker diarization system as a complete entity would require an extensive literature review, and might ultimately fail due to component description version mismatches. This paper therefore presents the first full conceptual description of the ICSI speaker diarization system as presented to the National Institute of Standards Technology Rich Transcription 2009 (NIST RT-09) evaluation, which consists of online and offline subsystems, multi-stream and single-stream implementations, and audio and audio-visual approaches. Some of the components, such as the online system, have not been previously described. The paper also includes all necessary preprocessing steps, such as Wiener filtering, speech activity detection and beamforming.

One of the main challenge in non-native speech recognition is how to handle acoustic variability present in multi-accented non-native speech with limited amount of training data. In this paper, we investigate an approach that addresses this challenge by using Kullback-Leibler divergence based hidden Markov models (KL-HMM). More precisely, the acoustic variability in the multi-accented speech is handled by using multilingual phoneme posterior probabilities, estimated by a multilayer perceptron trained on auxiliary data, as input feature for the KL-HMM system. With limited training data, we then build better acoustic models by exploiting the advantage that the KL-HMM system has fewer number of parameters. On HIWIRE corpus, the proposed approach yields a performance of 1.9% word error rate (WER) with 149 minutes of training data and a performance of 5.5% WER with 2 minutes of training data.

This paper presents a new approach to estimate "universal" phoneme posterior probabilities for mixed language speech recognition. More specifically, we propose a new theoretical framework to combine phoneme class posterior probabilities in a principled way by using (statistical) evidence about the language identity. We investigate the proposed approach in a mixed language environment (Speech-Dat(II)) consisting of five European languages. Our studies show that the proposed approach can yield significant improvements on a mixed language task, while maintaining the performance on monolingual tasks. Additionally, through a case study, we also demonstrate the potential benefits of the proposed approach for non-native speech recognition.

We propose a stochastic phoneme space transformation technique that allows the conversion of conditional source phoneme posterior probabilities (conditioned on the acoustics) into target phoneme posterior probabilities. The source and target phonemes can be in any language and phoneme format such as the International Phonetic Alphabet. The novel technique makes use of a Kullback-Leibler divergence based hidden Markov model and can be applied to non-native and accented speech recognition or used to adapt systems to under-resourced languages. In this paper, and in the context of hybrid HMM/MLP recognizers, we successfully apply the proposed approach to non-native English speech recognition on the HIWIRE dataset.

The following article presents a novel, adaptive initialization scheme that can be applied to most state-of-the-art Speaker Diarization algorithms, i.e. algorithms that use agglomerative hierarchical clustering with Bayesian Information Criterion (BIC) and Gaussian Mixture Models (GMMs) of frame-based cepstral features (MFCCs). The initialization method is a combination of the recently proposed “adaptive seconds per Gaussian” (ASPG) method and a new pre-clustering and number of initial clusters estimation method based on prosodic features. The presented initialization method has two important advantages. First, the method requires no manual tuning and is robust against file length and speaker count variations. Second, the method outperforms our previously used initialization methods on all benchmark files that were presented in the 2006, 2007, and 2009 NIST Rich Transcription (RT) evaluations and results in a Diarization Error Rate (DER) improvement of up to 67% (relative).

We investigate using state-of-the-art speaker diarization output for speech recognition purposes. While it seems obvious that speech recognition could benefit from the output of speaker diarization (“Who spoke when”) for effective feature normalization and model adaptation, such benefits have remained elusive in the very challenging domain of meeting recognition from distant microphones. In this study, we show that recognition gains are possible by careful post-processing of the diarization output. Still, recognition accuracy may suffer when the underlying diarization system performs worse than expected, even compared to far less sophisticated speaker-clustering techniques. We obtain a more accurate and robust overall system by combining recognition output with multiple speaker segmentations and clusterings. We evaluate our methods on data from the 2009 NIST Rich Transcription meeting recognition evaluation.

Multilingual speech recognition obviously involves numerous research challenges, including common phoneme sets, adaptation on limited amount of training data, as well as mixed language recognition (common in many countries, like Switzerland). In this latter case, it is not even possible to assume that one knows in advance the language being spoken. This is the context and motivation of the present work. We indeed investigate how current state-of-the-art speech recognition systems can be exploited in multilingual environments, where the language (from an assumed set of five possible languages, in our case) is not a priori known during recognition. We combine monolingual systems and extensively develop and compare different features and acoustic models. On Speech-Dat(II) datasets, and in the context of isolated words, we show that it is actually possible to approach the performances of monolingual systems even if the identity of the spoken language is not a priori known. Index Terms: speech recognition, multilingual speech recognition, combination of mono-lingual speech recognition systems, mixed language recognition. 1

Automatic language identification (LID) systems generally exploit acoustic knowledge, possibly enriched by explicit language specific phonotactic or lexical constraints. This paper investigates a new LID approach based on hierarchical multilayer perceptron (MLP) classifiers, where the first layer is a “universal phoneme set MLP classifier”. The resulting (multilingual) phoneme posterior sequence is fed into a second MLP taking a larger temporal context into account. The second MLP can learn/exploit implicitly different types of patterns/information such as confusion between phonemes and/or phonotactics for LID. We investigate the viability of the proposed approach by comparing it against two standard approaches which use phonotactic and lexical constraints with the universal phoneme set MLP classifier as emission probability estimator. On Speech-Dat(II) datasets of five European languages, the proposed approach yields significantly better performance compared to the two standard approaches. Index Terms: Language identification, multilingual processing, hierarchical MLP.

This paper investigates a typical speaker diarization system regarding its robustness against initialization parameter variation and presents a method to reduce manual tuning of these values significantly. The behavior of an agglomerative hierarchical clustering system is studied to determine which initialization parameters impact accuracy most. We show that the accuracy of typical systems is indeed very sensitive to the values chosen for the initialization parameters and factors such as the duration of speech in the recording. We then present a solution that reduces the sensitivity of the initialization values and therefore reduces the need for manual tuning significantly while at the same time increasing the accuracy of the system. For short meetings extracted from the previous (2006, 2007, and 2009) National Institute of Standards and Technology (NIST) Rich Transcription (RT) evaluation data, the decrease of the diarization error rate is up to 50% relative. The approach consists of a novel initialization parameter estimation method for speaker diarization that uses agglomerative clustering with Bayesian information criterion (BIC) and Gaussian mixture models (GMMs) of frame-based cepstral features (MFCCs). The estimation method balances the relationship between the optimal value of the seconds of speech data per Gaussian and the duration of the speech data and is combined with a novel nonuniform initialization method. This approach results in a system that performs better than the current ICSI baseline engine on datasets of the NIST RT evaluations of the years 2006, 2007, and 2009.

We investigate a state-of-the-art speaker diarization system regarding its behavior on meetings that are much shorter (from 500 seconds down to 100 seconds) than those typically analyzed in speaker diarization benchmarks. First, the problems inherent to this task are analyzed. Then, we propose an approach that consists of a novel initialization parameter estimation method for typical state-of-the-art diarization approaches. The estimation method balances the relationship between the optimal value of the duration of speech data per Gaussian and the duration of the speech data, which is verified experimentally for the first time in this article. As a result, the diarization error rate for short meetings extracted from the 2006, 2007, and 2009 NIST RT evaluation data is decreased by up to 50% relative.