Yifan Yang, Zheshu Song, Jianheng Zhuo, Mingyu Cui, Jinpeng Li, Bo Yang, Yexing Du, Ziyang Ma, Xunying Liu, Ziyuan Wang, Ke Li, Shuai Fan, Kai Yu, Wei-Qiang Zhang, Guoguo Chen, Xie Chen. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.

This paper describes the THUEE team's speech recognition system for the IARPA Open Automatic Speech Recognition Challenge (OpenASR21), with further experiment explorations. We achieve outstanding results under both the Constrained and Constrained-plus training conditions. For the Constrained training condition, we construct our basic ASR system based on the standard hybrid architecture. To alleviate the Out-Of-Vocabulary (OOV) problem, we extend the pronunciation lexicon using Grapheme-to-Phoneme (G2P) techniques for both OOV and potential new words. Standard acoustic model structures such as CNN-TDNN-F and CNN-TDNN-F-A are adopted. In addition, multiple data augmentation techniques are applied. For the Constrained-plus training condition, we use the self-supervised learning framework wav2vec2.0. We experiment with various fine-tuning techniques with the Connectionist Temporal Classification (CTC) criterion on top of the publicly available pre-trained model XLSR-53. We find that the frontend feature extractor plays an important role when applying the wav2vec2.0 pre-trained model to the encoder-decoder based CTC/Attention ASR architecture. Extra improvements can be achieved by using the CTC model finetuned in the target language as the frontend feature extractor.

This paper introduces GigaSpeech, an evolving, multi-domain English speech recognition corpus with 10,000 hours of high quality labeled audio suitable for supervised training, and 40,000 hours of total audio suitable for semi-supervised and unsupervised training.Around 40,000 hours of transcribed audio is first collected from audiobooks, podcasts and YouTube, covering both read and spontaneous speaking styles, and a variety of topics, such as arts, science, sports, etc.A new forced alignment and segmentation pipeline is proposed to create sentence segments suitable for speech recognition training, and to filter out segments with low-quality transcription.For system training, GigaSpeech provides five subsets of different sizes, 10h, 250h, 1000h, 2500h, and 10000h.For our 10,000-hour XL training subset, we cap the word error rate at 4% during the filtering/validation stage, and for all our other smaller training subsets, we cap it at 0%.The DEV and TEST evaluation sets, on the other hand, are re-processed by professional human transcribers to ensure high transcription quality.Baseline systems are provided for popular speech recognition toolkits, namely Athena, ESPnet, Kaldi and Pika.

Handcrafted pronunciation lexicons are widely used in modern speech recognition systems. Designing a pronunciation lexicon, however, requires tremendous amount of expert knowledge and effort, which is not practical when applying speech recognition techniques to low resource languages. In this paper, we are interested in developing speech recognition systems for logographic languages with only a small expert pronunciation lexicon. An iterative framework is proposed to generate and refine the phonetic transcripts of the training data, which will then be aligned to their word-level transcripts for grapheme-to-phoneme (G2P) model training. The G2P model trained this way covers graphemes that appear in the training transcripts (most of which are usually unseen in a small expert lexicon for logographic languages), therefore is able to generate pronunciations for all the words in the transcripts. The proposed lexicon generation procedure is evaluated on Cantonese speech recognition and keyword search tasks. Experiments show that starting from an expert lexicon of only 1K words, we are able to generate a lexicon that works reasonably well when compared with an expert-crafted lexicon of 5K words.

Despite the significant progress in speech recognition enabled by deep neural networks, poor performance persists in some scenarios. In this work, we focus on far-field speech recognition which remains challenging due to high levels of noise and reverberation in the captured speech signals. We propose to represent the stages of acoustic processing including beamforming, feature extraction, and acoustic modeling, as three components of a single unified computational network. The parameters of a frequency-domain beam-former are first estimated by a network based on features derived from the microphone channels. These filter coefficients are then applied to the array signals to form an enhanced signal. Conventional features are then extracted from this signal and passed to a second network that performs acoustic modeling for classification. The parameters of both the beamforming and acoustic modeling networks are trained jointly using back-propagation with a common cross-entropy objective function. In experiments on the AMI meeting corpus, we observed improvements by pre-training each sub-network with a network-specific objective function before joint training of both networks. The proposed method obtained a 3.2% absolute word error rate reduction compared to a conventional pipeline of independent processing stages.

In this paper, we extend the deep long short-term memory (DL-STM) recurrent neural networks by introducing gated direct connections between memory cells in adjacent layers. These direct links, called highway connections, enable unimpeded information flow across different layers and thus alleviate the gradient vanishing problem when building deeper LSTMs. We further introduce the latency-controlled bidirectional LSTMs (BLSTMs) which can exploit the whole history while keeping the latency under control. Efficient algorithms are proposed to train these novel networks using both frame and sequence discriminative criteria. Experiments on the AMI distant speech recognition (DSR) task indicate that we can train deeper LSTMs and achieve better improvement from sequence training with highway LSTMs (HLSTMs). Our novel model obtains 43.9/47.7% WER on AMI (SDM) dev and eval sets, outperforming all previous works. It beats the strong DNN and DLSTM baselines with 15.7% and 5.3% relative improvement respectively.

Multi-style training, using data which emulates a variety of possible test scenarios, is a popular approach towards robust acoustic modeling. However acoustic models capable of exploiting large amounts of training data in a comparatively short amount of training time are essential. In this paper we tackle the problem of reverberant speech recognition using 5500 hours of simulated reverberant data. We use time-delay neural network (TDNN) architecture, which is capable of tackling long-term interactions between speech and corrupting sources in reverberant environments. By sub-sampling the outputs at TDNN layers across time steps, training time is substantially reduced. Combining this with distributed-optimization we show that the TDNN can be trained in 3 days using up to 32 GPUs. Further, iVectors are used as an input to the neural network to perform instantaneous speaker and environment adaptation. Finally, recurrent neural network language models are applied to the lattices to further improve the performance. Our system is shown to provide state-of-the-art results in the IARPA ASpIRE challenge, with 26.5% WER on the dev Jest set.

We present a novel approach to query-by-example keyword spotting (KWS) using a long short-term memory (LSTM) recurrent neural network-based feature extractor. In our approach, we represent each keyword using a fixed-length feature vector obtained by running the keyword audio through a word-based LSTM acoustic model. We use the activations prior to the softmax layer of the LSTM as our keyword-vector. At runtime, we detect the keyword by extracting the same feature vector from a sliding window and computing a simple similarity score between this test vector and the keyword vector. With clean speech, we achieve 86% relative false rejection rate reduction at 0.5% false alarm rate when compared to a competitive phoneme posteriorgram with dynamic time warping KWS system, while the reduction in the presence of babble noise is 67%. Our system has a small memory footprint, low computational cost, and high precision, making it suitable for on-device applications.

This paper introduces a new corpus of read English speech, suitable for training and evaluating speech recognition systems. The LibriSpeech corpus is derived from audiobooks that are part of the LibriVox project, and contains 1000 hours of speech sampled at 16 kHz. We have made the corpus freely available for download, along with separately prepared language-model training data and pre-built language models. We show that acoustic models trained on LibriSpeech give lower error rate on the Wall Street Journal (WSJ) test sets than models trained on WSJ itself. We are also releasing Kaldi scripts that make it easy to build these systems.

In this paper we evaluate the WER improvement from modeling pronunciation probabilities and word-specific silence probabilities in speech recognition. We do this in the context of Finite State Transducer (FST)-based decoding, where pronunciation and silence probabilities are encoded in the lexicon (L) transducer. We describe a novel way to model word-dependent silence probabilities, where in addition to modeling the probability of silence following each individual word, we also model the probability of each word appearing after silence. All of these probabilities are estimated from aligned training data, with suitable smoothing. We conduct our experiments on four commonly used automatic speech recognition datasets, namely Wall Street Journal, Switchboard, TED-LIUM, and Librispeech. The improvement from modeling pronunciation and silence probabilities is small but fairly consistent across datasets.

In reverberant environments there are long term interactions between speech and corrupting sources. In this paper a time delay neural network (TDNN) architecture, capable of learning long term temporal relationships and translation invariant representations, is used for reverberation robust acoustic modeling. Further, iVectors are used as an input to the neural network to perform instantaneous speaker and environment adaptation, providing 10% relative improvement in word error rate. By subsampling the outputs at TDNN layers across time steps, training time is reduced. Using a parallel training algorithm we show that the TDNN can be trained on ∼ 5500 hours of speech data in 3 days using up to 32 GPUs. The TDNN is shown to provide results competitive with state of the art systems in the IARPA ASpIRE challenge, with 27.7% WER on the dev test set.

Modern speech recognition systems typically cluster triphone phonetic contexts using decision trees. In this paper we describe a way to build multiple complementary decision trees from the same data, for the purpose of system combination. We do this by jointly building the decision trees using an objective function that has an added entropy term to encourage diversity among the decision trees. After the trees are built, the systems are built in the standard way and the emission probabilities are combined during decoding. Experiments on multiple datasets show gains from the use of multiple trees, at the expense of evaluating multiple models in test time.

Our application requires a keyword spotting system with a small memory footprint, low computational cost, and high precision. To meet these requirements, we propose a simple approach based on deep neural networks. A deep neural network is trained to directly predict the keyword(s) or subword units of the keyword(s) followed by a posterior handling method producing a final confidence score. Keyword recognition results achieve 45% relative improvement with respect to a competitive Hidden Markov Model-based system, while performance in the presence of babble noise shows 39% relative improvement.

Spoken Term Detection (STD) focuses on finding instances of a particular spoken word or phrase in an audio corpus. Most STD systems have a two-step pipeline, ASR followed by search. Two approaches to search are common, Confusion Network (CN) based search and Finite State Transducer (FST) based search. In this paper, we examine combination of these two different search approaches, using the same ASR output. We find that the CN search performs better on shorter queries, and FST search performs better on longer queries. By combining the different search results from the same ASR decoding, we achieve better performance compared to either search approach on its own. We also find that this improvement is additive to the usual combination of decoder results using different modeling techniques.

The point process model (PPM) for keyword search is a wholeword parametric modeling framework based on the timing of phonetic events rather than the evolution of frame-level phonetic likelihoods. Recent progress in PPM training and decoding algorithms has yielded state-of-the-art phonetic search performance in high-resource settings, both in terms of accuracy and computational efficiency. In this paper, we consider PPM application to low-resource settings where the amount of transcribed speech is severely limited and the pronunciation dictionary is incomplete. By using (i) state-of-the-art deep neural network acoustic models to generate phonetic events and (ii) grapheme-to-phoneme conversion to generate pronunciations for out-of-vocabulary (OOV) keywords, we find the PPM system reaches state-of-the-art OOV search performance at a small computational cost. Moreover, due to their complementary methodologies, combining PPM outputs with the LVCSR baseline produces average relative ATWV improvements of 7% and 50% for in-vocabulary and OOV keywords, respectively (16% overall).

Provides an overview of a speech-to-text (STT) and keyword search (KWS) system architecture build primarily on the top of the Kaldi toolkit and expands on a few highlights. The system was developed as a part of the research efforts of the Radical team while participating in the IARPA Babel program. Our aim was to develop a general system pipeline which could be easily and rapidly deployed in any language, independently on the language script and phonological and linguistic features of the language.

We propose a simple but effective weighted finite state transducer (WFST) based framework for handling out-of-vocabulary (OOV) keywords in a speech search task. State-of-the-art large vocabulary continuous speech recognition (LVCSR) and keyword search (KWS) systems are developed for conversational telephone speech in Tagalog. Word-based and phone-based indexes are created from word lattices, the latter by using the LVCSR system's pronunciation lexicon. Pronunciations of OOV keywords are hypothesized via a standard grapheme-to-phoneme method. In-vocabulary proxies (word or phone sequences) are generated for each OOV keyword using WFST techniques that permit incorporation of a phone confusion matrix. Empirical results when searching for the Babel/NIST evaluation keywords in the Babel 10 hour development-test speech collection show that (i) searching for word proxies in the word index significantly outperforms searching for phonetic representations of OOV words in a phone index, and (ii) while phone confusion information yields minor improvement when searching a phone index, it yields up to 40% improvement in actual term weighted value when searching a word index with word proxies.

This paper quantifies the value of pronunciation lexicons in large vocabulary continuous speech recognition (LVCSR) systems that support keyword search (KWS) in low resource languages. State-of-the-art LVCSR and KWS systems are developed for conversational telephone speech in Tagalog, and the baseline lexicon is augmented via three different grapheme-to-phoneme models that yield increasing coverage of a large Tagalog word-list. It is demonstrated that while the increased lexical coverage - or reduced out-of-vocabulary (OOV) rate - leads to only modest (ca 1%-4%) improvements in word error rate, the concomitant improvements in actual term weighted value are as much as 60%. It is also shown that incorporating the augmented lexicons into the LVCSR system before indexing speech is superior to using them post facto, e.g., for approximate phonetic matching of OOV keywords in pre-indexed lattices. These results underscore the disproportionate importance of automatic lexicon augmentation for KWS in morphologically rich languages, and advocate for using them early in the LVCSR stage.