861 citations · 1k across the 13 of their papers we have counts for
15 papers
Clustering and Mining Accented Speech for Inclusive and Fair Speech Recognition
Jaeyoung Kim, Han Lu, Soheil Khorram +3
Modern automatic speech recognition (ASR) systems are typically trained on more than tens of thousands hours of speech data, which is one of the main factors for their great succes…
Contrastive Siamese Network for Semi-supervised Speech Recognition
Soheil Khorram, Jaeyoung Kim, Anshuman Tripathi +3
This paper introduces contrastive siamese (c-siam) network, an architecture for leveraging unlabeled acoustic data in speech recognition. c-siam is the first network that extracts…
Turn-to-Diarize: Online Speaker Diarization Constrained by Transformer Transducer Speaker Turn Detection
Wei Xia, Han Lu, Quan Wang +4
In this paper, we present a novel speaker diarization system for streaming on-device applications. In this system, we use a transformer transducer to detect the speaker turns, repr…
Reducing Streaming ASR Model Delay with Self Alignment
Jaeyoung Kim, Han Lu, Anshuman Tripathi +2
Reducing prediction delay for streaming end-to-end ASR models with minimal performance regression is a challenging problem. Constrained alignment is a well-known existing approach…
Transformer Transducer: One Model Unifying Streaming and Non-streaming Speech Recognition
Anshuman Tripathi, Jaeyoung Kim, Qian Zhang +2
In this paper we present a Transformer-Transducer model architecture and a training technique to unify streaming and non-streaming speech recognition models into one model. The mod…
A Density Ratio Approach to Language Model Fusion in End-To-End Automatic Speech Recognition
Erik McDermott, Hasim Sak, Ehsan Variani
This article describes a density ratio approach to integrating external Language Models (LMs) into end-to-end models for Automatic Speech Recognition (ASR). Applied to a Recurrent…
Transformer Transducer: A Streamable Speech Recognition Model with Transformer Encoders and RNN-T Loss
Qian Zhang, Han Lu, Hasim Sak +4
In this paper we present an end-to-end speech recognition model with Transformer encoders that can be used in a streaming speech recognition system. Transformer computation blocks…
Adversarial Training for Multilingual Acoustic Modeling
Ke Hu, Hasim Sak, Hank Liao
Multilingual training has been shown to improve acoustic modeling performance by sharing and transferring knowledge in modeling different languages. Knowledge sharing is usually ac…
Large-Scale Visual Speech Recognition
Brendan Shillingford, Yannis Assael, Matthew W. Hoffman +12
This work presents a scalable solution to open-vocabulary visual speech recognition. To achieve this, we constructed the largest existing visual speech recognition dataset, consist…
Exploring Architectures, Data and Units For Streaming End-to-End Speech Recognition with RNN-Transducer
Kanishka Rao, Haşim Sak, Rohit Prabhavalkar
We investigate training end-to-end speech recognition models with the recurrent neural network transducer (RNN-T): a streaming, all-neural, sequence-to-sequence architecture which…
Speech recognition for medical conversations
Chung-Cheng Chiu, Anshuman Tripathi, Katherine Chou +11
In this work we explored building automatic speech recognition models for transcribing doctor patient conversation. We collected a large scale dataset of clinical conversations ($1…
Neural Speech Recognizer: Acoustic-to-Word LSTM Model for Large Vocabulary Speech Recognition
Hagen Soltau, Hank Liao, Hasim Sak
We present results that show it is possible to build a competitive, greatly simplified, large vocabulary continuous speech recognition system with whole words as acoustic units. We…
Personalized Speech recognition on mobile devices
Ian McGraw, Rohit Prabhavalkar, Raziel Alvarez +8
We describe a large vocabulary speech recognition system that is accurate, has low latency, and yet has a small enough memory and computational footprint to run faster than real-ti…
Fast and Accurate Recurrent Neural Network Acoustic Models for Speech Recognition
Haşim Sak, Andrew Senior, Kanishka Rao +1
We have recently shown that deep Long Short-Term Memory (LSTM) recurrent neural networks (RNNs) outperform feed forward deep neural networks (DNNs) as acoustic models for speech re…
Long Short-Term Memory Based Recurrent Neural Network Architectures for Large Vocabulary Speech Recognition
Haşim Sak, Andrew Senior, Françoise Beaufays
Long Short-Term Memory (LSTM) is a recurrent neural network (RNN) architecture that has been designed to address the vanishing and exploding gradient problems of conventional RNNs.…