Decoder-only discrete-token language models have recently achieved significant success in automatic speech recognition. However, systematic analyses of how different modalities impact performance in specific scenarios remain limited. In this paper, we investigate the effects of multiple modalities on speech recognition accuracy on both synthetic and real-world datasets. Our experiments suggest that: (1) Integrating more modalities can increase accuracy but the benefit depends on the amount of auditory noise. We also show for the first time the benefit of combining audio, image context, and lip information in one speech recognition model. (2) Images as a supplementary modality for speech recognition provide their greatest benefit at moderate audio noise levels; moreover, they exhibit a different trend compared to inherently synchronized modalities like lip movements. (3) Performance improves on both synthetic and real-world datasets when the most relevant visual information is filtered as a preprocessing step.

K-12 school classrooms have proven to be a challenging environment for Automatic Speech Recognition (ASR) systems, both due to background noise and conversation, and differences in linguistic and acoustic properties from adult speech, on which the majority of ASR systems are trained and evaluated. We report on experiments to improve ASR for child speech in the classroom by training and fine-tuning transformer models on public corpora of adult and child speech augmented with classroom background noise. By tuning OpenAI’s Whisper model we achieve a 38% relative reduction in word error rate (WER) to 9.2% on the public MyST dataset of child speech – the lowest yet reported – and a 7% relative reduction to reach 54% WER on a more challenging classroom speech dataset (ISAT). We also introduce a novel beam hypothesis rescoring method that incorporates a speed-aware term to capture prior knowledge of human speaking rates, as well as a Large Language Model, to select among hypotheses. We demonstrate the effectiveness of this technique on both publicly-available datasets and a classroom speech dataset.

Endpoint (EP) detection is a key component of far-field speech recognition systems that assist the user through voice commands. The endpoint detector has to trade-off between accuracy and latency, since waiting longer reduces the cases of users being cut-off early. We propose a novel two-pass solution for endpointing, where the utterance endpoint detected from a first pass endpointer is verified by a 2nd-pass model termed EP Arbitrator. Our method improves the trade-off between early cut-offs and latency over a baseline endpointer, as tested on datasets including voice-assistant transactional queries, conversational speech, and the public SLURP corpus. We demonstrate that our method shows improvements regardless of the first-pass EP model used.

We introduce a variant of the endpoint (EP) detection problem in automatic speech recognition (ASR), which we call the end-of-speech (EOS) estimation. Given an utterance, EOS estimation aims to identify the timestamp when the utterance waveform has fully decayed and is then used to measure the EP latency. Accurate EOS estimation is difficult in large-scale streaming audio scenarios due to the hefty traffic and hardware limitations. To this end, we develop an efficient and accurate framework by performing force alignment on the 1-best ASR hypothesis. In particular, we propose to use binarized states sequences for alignment, which yields an EOS estimation robust to ASR hypothesis, and the estimation error is reduced by 28% compared to aligning on phoneme states. In addition, we further observe a 30% error reduction by applying the intermediate-stage embeddings of the encoder as additional features to compute the binary probabilities.

Current endpointing (EP) solutions learn in a supervised framework, which does not allow the model to incorporate feedback and improve in an online setting. Also, it is common practice to utilize costly grid-search to find the best configuration for an endpointing model. In this paper, we aim to provide a solution for adaptive endpointing by proposing an efficient method for choosing an optimal endpointing configuration given utterance-level audio features in an online setting, while avoiding hyperparameter grid-search. Our method does not require ground truth labels, and uses only online learning from reward signals. Specifically, we propose a deep contextual multi-armed bandit-based approach, combining the representational power of neural networks with the action exploration behavior of Thomp-son modeling algorithms. We compare our approach to several baselines, and show that our deep bandit models also succeed in reducing early cutoff errors while maintaining low latency.

Speech enhancement has recently achieved great success with various deep learning methods. However, most conventional speech enhancement systems are trained with supervised methods that impose two significant challenges. First, a majority of training datasets for speech enhancement systems are synthetic. When mixing clean speech and noisy corpora to create the synthetic datasets, domain mismatches occur between synthetic and real-world recordings of noisy speech or audio. Second, there is a trade-off between increasing speech enhancement performance and degrading speech recognition (ASR) performance. Thus, we propose an unsupervised loss function to tackle those two problems. Our function is developed by extending the MixIT loss function with speech recognition embedding and disentanglement loss. Our results show that the proposed function effectively improves the speech enhancement performance compared to a baseline trained in a supervised way on the noisy VoxCeleb dataset. While fully unsupervised training is unable to exceed the corresponding baseline, with joint super- and unsupervised training, the system is able to achieve similar speech quality and better ASR performance than the best supervised baseline.

We introduce ImportantAug, a technique to augment training data for speech classification and recognition models by adding noise to unimportant regions of the speech and not to important regions. Importance is predicted for each utterance by a data augmentation agent that is trained to maximize the amount of noise it adds while minimizing its impact on recognition performance. The effectiveness of our method is illustrated on version two of the Google Speech Commands (GSC) dataset. On the standard GSC test set, it achieves a 23.3% relative error rate reduction compared to conventional noise augmentation which applies noise to speech without regard to where it might be most effective. It also provides a 25.4% error rate reduction compared to a baseline without data augmentation. Additionally, the proposed ImportantAug outperforms the conventional noise augmentation and the baseline on two test sets with additional noise added.

We present an approach to reduce the performance disparity between geographic regions without degrading performance on the overall user population for ASR.A popular approach is to fine-tune the model with data from regions where the ASR model has a higher word error rate (WER).However, when the ASR model is adapted to get better performance on these high-WER regions, its parameters wander from the previous optimal values, which can lead to worse performance in other regions.In our proposed method, we utilize the elastic weight consolidation (EWC) regularization loss to identify directions in parameters space along which the ASR weights can vary to improve for high-error regions, while still maintaining performance on the speaker population overall.Our results demonstrate that EWC can reduce the word error rate (WER) in the region with highest WER by 3.2% relative while reducing the overall WER by 1.3% relative.We also evaluate the role of language and acoustic models in ASR fairness and propose a clustering algorithm to identify WER disparities based on geographic region.

Automatic speech recognition (ASR) has reached human performance on many clean speech corpora, but it remains worse than human listeners in noisy environments. This paper investigates whether this difference in performance might be due to a difference in the time-frequency regions that each listener utilizes in making their decisions and how these “important” regions change for ASRs using different acoustic models (AMs) and language models (LMs). We define important regions as time-frequency points in a spectrogram that tend to be audible when the listener correctly recognizes that utterance in noise. The evidence from this study indicates that a neural network AM attends to regions that are more similar to those of humans (capturing certain high-energy regions) than those of a traditional Gaussian mixture model (GMM) AM. Our analysis also shows that the neural network AM has not yet captured all the cues that human listeners utilize, such as certain transitions between silence and high speech energy. We also find that differences in important time-frequency regions tend to track differences in accuracy on specific words in a test sentence, suggesting a connection. Because of this connection, adapting an ASR to attend to the same regions humans use might improve its generalization in noise.

In this paper, we propose a metric that we call the structured saliency benchmark (SSBM) to evaluate importance maps computed for automatic speech recognizers on individual utterances. These maps indicate time-frequency points of the utterance that are most important for correct recognition of a target word. Our evaluation technique is not only suitable for standard classification tasks, but is also appropriate for structured prediction tasks like sequence-to-sequence models. Additionally, we use this approach to perform a large scale comparison of the importance maps created by our previously introduced technique using "bubble noise" to identify important points through correlation with a baseline approach based on smoothed speech energy and forced alignment. Our results show that the bubble analysis approach is better at identifying important speech regions than this baseline on 100 sentences from the AMI corpus.