477 citations · 1.1k across the 39 of their papers we have counts for
23 papers · 1 filter
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…
Modality Confidence Aware Training for Robust End-to-End Spoken Language Understanding
Suyoun Kim, Akshat Shrivastava, Duc Le +3
End-to-end (E2E) spoken language understanding (SLU) systems that generate a semantic parse from speech have become more promising recently. This approach uses a single model that…
Massively Multilingual ASR on 70 Languages: Tokenization, Architecture, and Generalization Capabilities
Andros Tjandra, Nayan Singhal, David Zhang +4
End-to-end multilingual ASR has become more appealing because of several reasons such as simplifying the training and deployment process and positive performance transfer from high…
Deliberation Model for On-Device Spoken Language Understanding
Duc Le, Akshat Shrivastava, Paden Tomasello +4
We propose a novel deliberation-based approach to end-to-end (E2E) spoken language understanding (SLU), where a streaming automatic speech recognition (ASR) model produces the firs…
Streaming parallel transducer beam search with fast-slow cascaded encoders
Jay Mahadeokar, Yangyang Shi, Ke Li +5
Streaming ASR with strict latency constraints is required in many speech recognition applications. In order to achieve the required latency, streaming ASR models sacrifice accuracy…
Neural-FST Class Language Model for End-to-End Speech Recognition
Antoine Bruguier, Duc Le, Rohit Prabhavalkar +7
We propose Neural-FST Class Language Model (NFCLM) for end-to-end speech recognition, a novel method that combines neural network language models (NNLMs) and finite state transduce…
Evaluating User Perception of Speech Recognition System Quality with Semantic Distance Metric
Suyoun Kim, Duc Le, Weiyi Zheng +6
Measuring automatic speech recognition (ASR) system quality is critical for creating user-satisfying voice-driven applications. Word Error Rate (WER) has been traditionally used to…
Collaborative Training of Acoustic Encoders for Speech Recognition
Varun Nagaraja, Yangyang Shi, Ganesh Venkatesh +3
On-device speech recognition requires training models of different sizes for deploying on devices with various computational budgets. When building such different models, we can be…
Dynamic Encoder Transducer: A Flexible Solution For Trading Off Accuracy For Latency
Yangyang Shi, Varun Nagaraja, Chunyang Wu +9
We propose a dynamic encoder transducer (DET) for on-device speech recognition. One DET model scales to multiple devices with different computation capacities without retraining or…
Semantic Distance: A New Metric for ASR Performance Analysis Towards Spoken Language Understanding
Suyoun Kim, Abhinav Arora, Duc Le +4
Word Error Rate (WER) has been the predominant metric used to evaluate the performance of automatic speech recognition (ASR) systems. However, WER is sometimes not a good indicator…
Contextualized Streaming End-to-End Speech Recognition with Trie-Based Deep Biasing and Shallow Fusion
Duc Le, Mahaveer Jain, Gil Keren +9
How to leverage dynamic contextual information in end-to-end speech recognition has remained an active research area. Previous solutions to this problem were either designed for sp…
Deep Shallow Fusion for RNN-T Personalization
Duc Le, Gil Keren, Julian Chan +3
End-to-end models in general, and Recurrent Neural Network Transducer (RNN-T) in particular, have gained significant traction in the automatic speech recognition community in the l…
Alignment Restricted Streaming Recurrent Neural Network Transducer
Jay Mahadeokar, Yuan Shangguan, Duc Le +6
There is a growing interest in the speech community in developing Recurrent Neural Network Transducer (RNN-T) models for automatic speech recognition (ASR) applications. RNN-T is t…
Streaming Attention-Based Models with Augmented Memory for End-to-End Speech Recognition
Ching-Feng Yeh, Yongqiang Wang, Yangyang Shi +4
Attention-based models have been gaining popularity recently for their strong performance demonstrated in fields such as machine translation and automatic speech recognition. One m…
Improved Neural Language Model Fusion for Streaming Recurrent Neural Network Transducer
Suyoun Kim, Yuan Shangguan, Jay Mahadeokar +4
Recurrent Neural Network Transducer (RNN-T), like most end-to-end speech recognition model architectures, has an implicit neural network language model (NNLM) and cannot easily lev…
AIPNet: Generative Adversarial Pre-training of Accent-invariant Networks for End-to-end Speech Recognition
Yi-Chen Chen, Zhaojun Yang, Ching-Feng Yeh +2
As one of the major sources in speech variability, accents have posed a grand challenge to the robustness of speech recognition systems. In this paper, our goal is to build a unifi…
RNN-T For Latency Controlled ASR With Improved Beam Search
Mahaveer Jain, Kjell Schubert, Jay Mahadeokar +5
Neural transducer-based systems such as RNN Transducers (RNN-T) for automatic speech recognition (ASR) blend the individual components of a traditional hybrid ASR systems (acoustic…
Transformer-based Acoustic Modeling for Hybrid Speech Recognition
Yongqiang Wang, Abdelrahman Mohamed, Duc Le +10
We propose and evaluate transformer-based acoustic models (AMs) for hybrid speech recognition. Several modeling choices are discussed in this work, including various positional emb…
End-to-end contextual speech recognition using class language models and a token passing decoder
Zhehuai Chen, Mahaveer Jain, Yongqiang Wang +2
End-to-end modeling (E2E) of automatic speech recognition (ASR) blends all the components of a traditional speech recognition system into a unified model. Although it simplifies tr…
Towards Language-Universal End-to-End Speech Recognition
Suyoun Kim, Michael L. Seltzer
Building speech recognizers in multiple languages typically involves replicating a monolingual training recipe for each language, or utilizing a multi-task learning approach where…
Improved training for online end-to-end speech recognition systems
Suyoun Kim, Michael L. Seltzer, Jinyu Li +1
Achieving high accuracy with end-to-end speech recognizers requires careful parameter initialization prior to training. Otherwise, the networks may fail to find a good local optimu…
Large-Scale Domain Adaptation via Teacher-Student Learning
Jinyu Li, Michael L. Seltzer, Xi Wang +2
High accuracy speech recognition requires a large amount of transcribed data for supervised training. In the absence of such data, domain adaptation of a well-trained acoustic mode…
Achieving Human Parity in Conversational Speech Recognition
W. Xiong, J. Droppo, X. Huang +5
Conversational speech recognition has served as a flagship speech recognition task since the release of the Switchboard corpus in the 1990s. In this paper, we measure the human err…