Practice and recent evidence show that state-of-the-art (SotA) automatic speech recognition (ASR) systems do not perform equally well for all speaker groups. Many factors can cause this bias against different speaker groups. This paper, for the first time, systematically quantifies and finds speech recognition bias against gender, age, regional accents and non-native accents, and investigates the origin of this bias by investigating bias cross-lingually (i.e., Dutch and Mandarin) and for two different SotA ASR architectures (a hybrid DNN-HMM and an attention based end-to-end (E2E) model) through a phoneme error analysis. The results show that only a fraction of the bias can be explained by pronunciation differences between speaker groups, and that in order to mitigate bias, language- and architecture specific solutions need to be found.

In this paper, we build and compare multiple speech systems for the automatic evaluation of the severity of a speech impairment due to oral cancer, based on spontaneous speech. To be able to build and evaluate such systems, we collected a new spontaneous oral cancer speech corpus from YouTube consisting of 124 utterances rated by 100 non-expert listeners and one trained speech-language pathologist, which we made publicly available. We evaluated the systems in two scenarios: a scenario where transcriptions were available (reference-based) and a scenario where transcriptions might not be available (reference-free). The results of extensive experiments showed that (1) when transcriptions were available, the highest correlation with the human severity ratings was obtained using an automatic speech recognition (ASR) retrained with oral cancer speech. (2) When transcriptions were not available, the best results were achieved by a LASSO model using modulation spectrum features. (3) We found that naive listeners’ ratings are highly similar to the speech pathologist’s ratings for speech severity evaluation. (4) The use of binary labels led to lower correlations of the automatic methods with the human ratings than using severity scores.

In this paper, we investigate several existing and a new state-of-the-art generative adversarial network-based (GAN) voice conversion method for enhancing dysarthric speech for improved dysarthric speech recognition. We compare key components of existing methods as part of a rigorous ablation study to find the most effective solution to improve dysarthric speech recognition. We find that straightforward signal processing methods such as stationary noise removal and vocoder-based time stretching lead to dysarthric speech recognition results comparable to those obtained when using state-of-the-art GAN-based voice conversion methods as measured using a phoneme recognition task. Additionally, our proposed solution of a combination of MaskCycleGAN-VC and time stretching is able to improve the phoneme recognition results for certain dysarthric speakers compared to our time stretched baseline.

In this paper, we introduce a new corpus of oral cancer speech and present our study on the automatic recognition and analysis of oral cancer speech. A two-hour English oral cancer speech dataset is collected from YouTube. Formulated as a low-resource oral cancer ASR task, we investigate three acoustic modelling approaches that previously have worked well with low-resource scenarios using two different architectures; a hybrid architecture and a transformer-based end-to-end (E2E) model: (1) a retraining approach; (2) a speaker adaptation approach; and (3) a disentangled representation learning approach (only using the hybrid architecture). The approaches achieve a (1) 4.7% (hybrid) and 7.5% (E2E); (2) 7.7%; and (3) 2.0% absolute word error rate reduction, respectively, compared to a baseline system which is not trained on oral cancer speech. A detailed analysis of the speech recognition results shows that (1) plosives and certain vowels are the most difficult sounds to recognise in oral cancer speech — this problem is successfully alleviated by our proposed approaches; (3) however these sounds are also relatively poorly recognised in the case of healthy speech with the exception of/p/. (2) recognition performance of certain phonemes is strongly data-dependent; (4) In terms of the manner of articulation, E2E performs better with the exception of vowels — however, vowels have a large contribution to overall performance. As for the place of articulation, vowels, labiodentals, dentals and glottals are better captured by hybrid models, E2E is better on bilabial, alveolar, postalveolar, palatal and velar information. (5) Finally, our analysis provides some guidelines for selecting words that can be used as voice commands for ASR systems for oral cancer speakers.

The idea of combining multiple languages’ recordings to train a single automatic speech recognition (ASR) model brings the promise of the emergence of universal speech representation. Recently, a Transformer encoder-decoder model has been shown to leverage multilingual data well in IPA transcriptions of languages presented during training. However, the representations it learned were not successful in zero-shot transfer to unseen languages. Because that model lacks an explicit factorization of the acoustic model (AM) and language model (LM), it is unclear to what degree the performance suffered from differences in pronunciation or the mismatch in phono-tactics. To gain more insight into the factors limiting zero-shot ASR transfer, we replace the encoder-decoder with a hybrid ASR system consisting of a separate AM and LM. Then, we perform an extensive evaluation of monolingual, multilingual, and crosslingual (zero-shot) acoustic and language models on a set of 13 phonetically diverse languages. We show that the gain from modeling crosslingual phonotactics is limited, and imposing a too strong model can hurt the zero-shot transfer. Furthermore, we find that a multilingual LM hurts a multilingual ASR system’s performance, and retaining only the target language’s phonotactic data in LM training is preferable.

This paper proposes a new model, referred to as the show and speak (SAS) model that, for the first time, is able to directly synthesize spoken descriptions of images, bypassing the need for any text or phonemes. The basic structure of SAS is an encoder-decoder architecture that takes an image as input and predicts the spectrogram of speech that describes this image. The final speech audio is obtained from the predicted spectrogram via WaveNet. Extensive experiments on the public benchmark database Flickr8k demonstrate that the proposed SAS is able to synthesize natural spoken descriptions for images, indicating that synthesizing spoken descriptions for images while bypassing text and phonemes is feasible.

This paper tackles automatically discovering phone-like acoustic units (AUD) from unlabeled speech data. Past studies usually proposed single-step approaches. We propose a two-stage approach: the first stage learns a subword-discriminative feature representation and the second stage applies clustering to the learned representation and obtains phone-like clusters as the discovered acoustic units. In the first stage, a recently proposed method in the task of unsupervised subword modeling is improved by replacing a monolingual out-of-domain (OOD) ASR system with a multilingual one to create a subword-discriminative representation that is more language-independent. In the second stage, segment-level k-means is adopted, and two methods to represent the variable-length speech segments as fixed-dimension feature vectors are compared. Experiments on a very low-resource Mboshi language corpus show that our approach outperforms state-of-the-art AUD in both normalized mutual information (NMI) and F-score. The multilingual ASR improved upon the monolingual ASR in providing OOD phone labels and in estimating the phone boundaries. A comparison of our systems with and without knowing the ground-truth phone boundaries showed a 16% NMI performance gap, suggesting that the current approach can significantly benefit from improved phone boundary estimation.

Speech signal is constituted and contributed by various informative factors, such as linguistic content and speaker characteristic. There have been notable recent studies attempting to factorize speech signal into these individual factors without requiring any annotation. These studies typically assume continuous representation for linguistic content, which is not in accordance with general linguistic knowledge and may make the extraction of speaker information less successful. This paper proposes the mixture factorized auto-encoder (mFAE) for unsupervised deep factorization. The encoder part of mFAE comprises a frame tokenizer and an utterance embedder. The frame tokenizer models linguistic content of input speech with a discrete categorical distribution. It performs frame clustering by assigning each frame a soft mixture label. The utterance embedder generates an utterance-level vector representation. A frame decoder serves to reconstruct speech features from the encoders' outputs. The mFAE is evaluated on speaker verification (SV) task and unsupervised subword modeling (USM) task. The SV experiments on VoxCeleb 1 show that the utterance embedder is capable of extracting speaker-discriminative embeddings with performance comparable to a x-vector baseline. The USM experiments on ZeroSpeech 2017 dataset verify that the frame tokenizer is able to capture linguistic content and the utterance embedder can acquire speaker-related information.

This study addresses unsupervised subword modeling, i.e., learning feature representations that can distinguish subword units of a language. The proposed approach adopts a two-stage bottleneck feature (BNF) learning framework, consisting of autoregressive predictive coding (APC) as a front-end and a DNN-BNF model as a back-end. APC pretrained features are set as input features to a DNN-BNF model. A language-mismatched ASR system is used to provide cross-lingual phone labels for DNN-BNF model training. Finally, BNFs are extracted as the subword-discriminative feature representation. A second aim of this work is to investigate the robustness of our approach's effectiveness to different amounts of training data. The results on Libri-light and the ZeroSpeech 2017 databases show that APC is effective in front-end feature pretraining. Our whole system outperforms the state of the art on both databases. Cross-lingual phone labels for English data by a Dutch ASR outperform those by a Mandarin ASR, possibly linked to the larger similarity of Dutch compared to Mandarin with English. Our system is less sensitive to training data amount when the training data is over 50 hours. APC pretraining leads to a reduction of needed training material from over 5,000 hours to around 200 hours with little performance degradation.

This paper presents an investigation into speaker-invariant feature learning and domain adaptation for language recognition (LR) with short utterances. While following the conventional design of i-vector front-end and probabilistic linear discriminant analysis (PLDA) back-end, we propose to apply speaker adversarial multi-task learning (AMTL) to aim explicitly at learning speaker-invariant multilingual bottleneck features and perform unsupervised PLDA adaptation to alleviate performance degradation caused by domain mismatch between training and test data. Through a demo experiment, we show the adverse effect of domain mismatch and motivate the necessity of domain adaptation. LR experiments are carried out with the AP17-OLR challenge dataset to evaluate the effectiveness of the proposed methods in comparison with the state of the art. The results show that both speaker AMTL and unsupervised PLDA adaptation contribute significantly to performance improvement on the short-duration LR task. The effectiveness of PLDA adaptation is found to be insensitive to the number of clusters assumed in unsupervised data labeling. Our best system outperforms the state-of-the-art system of AP17-OLR and shows relative improvements of 6.98% in terms of Cavgand 4.80% in terms of EER on 1-second test set.

This study tackles unsupervised subword modeling in the zero-resource scenario, learning frame-level speech representation that is phonetically discriminative and speaker-invariant, using only untranscribed speech for target languages. Frame label acquisition is an essential step in solving this problem. High quality frame labels should be in good consistency with golden transcriptions and robust to speaker variation. We propose to improve frame label acquisition in our previously adopted deep neural network-bottleneck feature (DNN-BNF) architecture by applying the factorized hierarchical variational autoencoder (FHVAE). FHVAEs learn to disentangle linguistic content and speaker identity information encoded in speech. By discarding or unifying speaker information, speaker-invariant features are learned and fed as inputs to DPGMM frame clustering and DNN-BNF training. Experiments conducted on ZeroSpeech 2017 show that our proposed approaches achieve $2.4\%$ and $0.6\%$ absolute ABX error rate reductions in across- and within-speaker conditions, comparing to the baseline DNN-BNF system without applying FHVAEs. Our proposed approaches significantly outperform vocal tract length normalization in improving frame labeling and subword modeling.

This study addresses the problem of unsupervised subword unit discovery from untranscribed speech. It forms the basis of the ultimate goal of ZeroSpeech 2019, building text-to-speech systems without text labels. In this work, unit discovery is formulated as a pipeline of phonetically discriminative feature learning and unit inference. One major difficulty in robust unsupervised feature learning is dealing with speaker variation. Here the robustness towards speaker variation is achieved by applying adversarial training and FHVAE based disentangled speech representation learning. A comparison of the two approaches as well as their combination is studied in a DNN-bottleneck feature (DNN-BNF) architecture. Experiments are conducted on ZeroSpeech 2019 and 2017. Experimental results on ZeroSpeech 2017 show that both approaches are effective while the latter is more prominent, and that their combination brings further marginal improvement in across-speaker condition. Results on ZeroSpeech 2019 show that in the ABX discriminability task, our approaches significantly outperform the official baseline, and are competitive to or even outperform the official topline. The proposed unit sequence smoothing algorithm improves synthesis quality, at a cost of slight decrease in ABX discriminability.

This research addresses the problem of acoustic modeling of low-resource languages for which transcribed training data is absent. The goal is to learn robust frame-level feature representations that can be used to identify and distinguish subword-level speech units. The proposed feature representations comprise various types of multilingual bottleneck features (BNFs) that are obtained via multi-task learning of deep neural networks (MTL-DNN). One of the key problems is how to acquire high-quality frame labels for untranscribed training data to facilitate supervised DNN training. It is shown that learning of robust BNF representations can be achieved by effectively leveraging transcribed speech data and well-trained automatic speech recognition (ASR) systems from one or more out-of-domain (resource-rich) languages. Out-of-domain ASR systems can be applied to perform speaker adaptation with untranscribed training data of the target language, and to decode the training speech into frame-level labels for DNN training. It is also found that better frame labels can be generated by considering temporal dependency in speech when performing frame clustering. The proposed methods of feature learning are evaluated on the standard task of unsupervised subword modeling in Track 1 of the ZeroSpeech 2017 Challenge. The best performance achieved by our system is 9.7% in terms of across-speaker triphone minimal-pair ABX error rate, which is comparable to the best systems reported recently. Lastly, our investigation reveals that the closeness between target languages and out-of-domain languages and the amount of available training data for individual target languages could have significant impact on the goodness of learned features.

This paper describes an investigation on automatic speech assessment for people with aphasia (PWA) using a DNN based automatic speech recognition (ASR) system. The main problems being addressed are the lack of training speech in the intended application domain and the relevant degradation of ASR performance for impaired speech of PWA. We adopt the TDNN-BLSTM structure for acoustic modeling and apply the technique of multi-task learning with large amount of domain-mismatched data. This leads to a significant improvement on the recognition accuracy, as compared with a conventional single-task learning DNN system. To facilitate the extraction of robust text features for quantifying language impairment in PWA speech, we propose to incorporate N-best hypotheses and confusion network representation of the ASR output. The severity of impairment is predicted from text features and supra-segmental duration features using different regression models. Experimental results show a high correlation of 0.842 between the predicted severity level and the subjective Aphasia Quotient score.