5 citations · 8 across the 13 of their papers we have counts for
14 papers
Text Injection for Neural Contextual Biasing
Zhong Meng, Zelin Wu, Rohit Prabhavalkar +5
Neural contextual biasing effectively improves automatic speech recognition (ASR) for crucial phrases within a speaker's context, particularly those that are infrequent in the trai…
Improving Joint Speech-Text Representations Without Alignment
Cal Peyser, Zhong Meng, Ke Hu +5
The last year has seen astonishing progress in text-prompted image generation premised on the idea of a cross-modal representation space in which the text and image domains are rep…
A Comparison of Semi-Supervised Learning Techniques for Streaming ASR at Scale
Cal Peyser, Michael Picheny, Kyunghyun Cho +3
Unpaired text and audio injection have emerged as dominant methods for improving ASR performance in the absence of a large labeled corpus. However, little guidance exists on deploy…
Dual Learning for Large Vocabulary On-Device ASR
Cal Peyser, Ronny Huang, Tara Sainath +3
Dual learning is a paradigm for semi-supervised machine learning that seeks to leverage unsupervised data by solving two opposite tasks at once. In this scheme, each model is used…
E2E Segmentation in a Two-Pass Cascaded Encoder ASR Model
W. Ronny Huang, Shuo-Yiin Chang, Tara N. Sainath +7
We explore unifying a neural segmenter with two-pass cascaded encoder ASR into a single model. A key challenge is allowing the segmenter (which runs in real-time, synchronously wit…
Towards Disentangled Speech Representations
Cal Peyser, Ronny Huang Andrew Rosenberg Tara N. Sainath, Michael Picheny +1
The careful construction of audio representations has become a dominant feature in the design of approaches to many speech tasks. Increasingly, such approaches have emphasized "dis…
E2E Segmenter: Joint Segmenting and Decoding for Long-Form ASR
W. Ronny Huang, Shuo-yiin Chang, David Rybach +5
Improving the performance of end-to-end ASR models on long utterances ranging from minutes to hours in length is an ongoing challenge in speech recognition. A common solution is to…
Improving Rare Word Recognition with LM-aware MWER Training
Weiran Wang, Tongzhou Chen, Tara N. Sainath +10
Language models (LMs) significantly improve the recognition accuracy of end-to-end (E2E) models on words rarely seen during training, when used in either the shallow fusion or the…
Sentence-Select: Large-Scale Language Model Data Selection for Rare-Word Speech Recognition
W. Ronny Huang, Cal Peyser, Tara N. Sainath +3
Language model fusion helps smart assistants recognize words which are rare in acoustic data but abundant in text-only corpora (typed search logs). However, such corpora have prope…
Lookup-Table Recurrent Language Models for Long Tail Speech Recognition
W. Ronny Huang, Tara N. Sainath, Cal Peyser +3
We introduce Lookup-Table Language Models (LookupLM), a method for scaling up the size of RNN language models with only a constant increase in the floating point operations, by inc…
Improving Tail Performance of a Deliberation E2E ASR Model Using a Large Text Corpus
Cal Peyser, Sepand Mavandadi, Tara N. Sainath +3
End-to-end (E2E) automatic speech recognition (ASR) systems lack the distinct language model (LM) component that characterizes traditional speech systems. While this simplifies the…
Improving Proper Noun Recognition in End-to-End ASR By Customization of the MWER Loss Criterion
Cal Peyser, Tara N. Sainath, Golan Pundak
Proper nouns present a challenge for end-to-end (E2E) automatic speech recognition (ASR) systems in that a particular name may appear only rarely during training, and may have a pr…
A Streaming On-Device End-to-End Model Surpassing Server-Side Conventional Model Quality and Latency
Tara N. Sainath, Yanzhang He, Bo Li +26
Thus far, end-to-end (E2E) models have not been shown to outperform state-of-the-art conventional models with respect to both quality, i.e., word error rate (WER), and latency, i.e…
Improving Performance of End-to-End ASR on Numeric Sequences
Cal Peyser, Hao Zhang, Tara N. Sainath +1
Recognizing written domain numeric utterances (e.g. I need $1.25.) can be challenging for ASR systems, particularly when numeric sequences are not seen during training. This out-of…