2 citations · 4 across the 9 of their papers we have counts for
9 papers
Aligner-Encoders: Self-Attention Transformers Can Be Self-Transducers
Adam Stooke, Rohit Prabhavalkar, Khe Chai Sim +1
Modern systems for automatic speech recognition, including the RNN-Transducer and Attention-based Encoder-Decoder (AED), are designed so that the encoder is not required to alter t…
TransformerFAM: Feedback attention is working memory
Dongseong Hwang, Weiran Wang, Zhuoyuan Huo +2
While Transformers have revolutionized deep learning, their quadratic attention complexity hinders their ability to process infinitely long inputs. We propose Feedback Attention Me…
Hierarchical Recurrent Adapters for Efficient Multi-Task Adaptation of Large Speech Models
Tsendsuren Munkhdalai, Youzheng Chen, Khe Chai Sim +3
Parameter efficient adaptation methods have become a key mechanism to train large pre-trained models for downstream tasks. However, their per-task parameter overhead is considered…
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…
Contextual Biasing with the Knuth-Morris-Pratt Matching Algorithm
Weiran Wang, Zelin Wu, Diamantino Caseiro +10
Contextual biasing refers to the problem of biasing the automatic speech recognition (ASR) systems towards rare entities that are relevant to the specific user or application scena…
Massive End-to-end Models for Short Search Queries
Weiran Wang, Rohit Prabhavalkar, Dongseong Hwang +11
In this work, we investigate two popular end-to-end automatic speech recognition (ASR) models, namely Connectionist Temporal Classification (CTC) and RNN-Transducer (RNN-T), for of…
Improving Speech Recognition for African American English With Audio Classification
Shefali Garg, Zhouyuan Huo, Khe Chai Sim +11
Automatic speech recognition (ASR) systems have been shown to have large quality disparities between the language varieties they are intended or expected to recognize. One way to m…
Modular Domain Adaptation for Conformer-Based Streaming ASR
Qiujia Li, Bo Li, Dongseong Hwang +2
Speech data from different domains has distinct acoustic and linguistic characteristics. It is common to train a single multidomain model such as a Conformer transducer for speech…
Non-Parallel Voice Conversion for ASR Augmentation
Gary Wang, Andrew Rosenberg, Bhuvana Ramabhadran +4
Automatic speech recognition (ASR) needs to be robust to speaker differences. Voice Conversion (VC) modifies speaker characteristics of input speech. This is an attractive feature…