184 citations · 337 across the 15 of their papers we have counts for
16 papers
Schema Augmentation for Zero-Shot Domain Adaptation in Dialogue State Tracking
Christopher Richardson, Roshan Sharma, Neeraj Gaur +3
Zero-shot domain adaptation for dialogue state tracking (DST) remains a challenging problem in task-oriented dialogue (TOD) systems, where models must generalize to target domains…
ASTRA: Aligning Speech and Text Representations for Asr without Sampling
Neeraj Gaur, Rohan Agrawal, Gary Wang +3
This paper introduces ASTRA, a novel method for improving Automatic Speech Recognition (ASR) through text injection.Unlike prevailing techniques, ASTRA eliminates the need for samp…
IndicVoices: Towards building an Inclusive Multilingual Speech Dataset for Indian Languages
Tahir Javed, Janki Atul Nawale, Eldho Ittan George +18
We present INDICVOICES, a dataset of natural and spontaneous speech containing a total of 7348 hours of read (9%), extempore (74%) and conversational (17%) audio from 16237 speaker…
Audio-AdapterFusion: A Task-ID-free Approach for Efficient and Non-Destructive Multi-task Speech Recognition
Hillary Ngai, Rohan Agrawal, Neeraj Gaur +3
Adapters are an efficient, composable alternative to full fine-tuning of pre-trained models and help scale the deployment of large ASR models to many tasks. In practice, a task ID…
Using Text Injection to Improve Recognition of Personal Identifiers in Speech
Yochai Blau, Rohan Agrawal, Lior Madmony +7
Accurate recognition of specific categories, such as persons' names, dates or other identifiers is critical in many Automatic Speech Recognition (ASR) applications. As these catego…
Universal Automatic Phonetic Transcription into the International Phonetic Alphabet
Chihiro Taguchi, Yusuke Sakai, Parisa Haghani +1
This paper presents a state-of-the-art model for transcribing speech in any language into the International Phonetic Alphabet (IPA). Transcription of spoken languages into IPA is a…
Google USM: Scaling Automatic Speech Recognition Beyond 100 Languages
Yu Zhang, Wei Han, James Qin +24
We introduce the Universal Speech Model (USM), a single large model that performs automatic speech recognition (ASR) across 100+ languages. This is achieved by pre-training the enc…
Accelerating RNN-T Training and Inference Using CTC guidance
Yongqiang Wang, Zhehuai Chen, Chengjian Zheng +3
We propose a novel method to accelerate training and inference process of recurrent neural network transducer (RNN-T) based on the guidance from a co-trained connectionist temporal…
Streaming End-to-End Multilingual Speech Recognition with Joint Language Identification
Chao Zhang, Bo Li, Tara Sainath +4
Language identification is critical for many downstream tasks in automatic speech recognition (ASR), and is beneficial to integrate into multilingual end-to-end ASR as an additiona…
A Language Agnostic Multilingual Streaming On-Device ASR System
Bo Li, Tara N. Sainath, Ruoming Pang +9
On-device end-to-end (E2E) models have shown improvements over a conventional model on English Voice Search tasks in both quality and latency. E2E models have also shown promising…
Unsupervised Data Selection via Discrete Speech Representation for ASR
Zhiyun Lu, Yongqiang Wang, Yu Zhang +3
Self-supervised learning of speech representations has achieved impressive results in improving automatic speech recognition (ASR). In this paper, we show that data selection is im…
Input Length Matters: Improving RNN-T and MWER Training for Long-form Telephony Speech Recognition
Zhiyun Lu, Yanwei Pan, Thibault Doutre +5
End-to-end models have achieved state-of-the-art results on several automatic speech recognition tasks. However, they perform poorly when evaluated on long-form data, e.g., minutes…
Scaling End-to-End Models for Large-Scale Multilingual ASR
Bo Li, Ruoming Pang, Tara N. Sainath +7
Building ASR models across many languages is a challenging multi-task learning problem due to large variations and heavily unbalanced data. Existing work has shown positive transfe…
Lingvo: a Modular and Scalable Framework for Sequence-to-Sequence Modeling
Jonathan Shen, Patrick Nguyen, Yonghui Wu +88
Lingvo is a Tensorflow framework offering a complete solution for collaborative deep learning research, with a particular focus towards sequence-to-sequence models. Lingvo models a…
From Audio to Semantics: Approaches to end-to-end spoken language understanding
Parisa Haghani, Arun Narayanan, Michiel Bacchiani +6
Conventional spoken language understanding systems consist of two main components: an automatic speech recognition module that converts audio to a transcript, and a natural languag…
Toward domain-invariant speech recognition via large scale training
Arun Narayanan, Ananya Misra, Khe Chai Sim +6
Current state-of-the-art automatic speech recognition systems are trained to work in specific `domains', defined based on factors like application, sampling rate and codec. When su…