Search Results for author: Jay Mahadeokar

Found 25 papers, 2 papers with code

Towards General-Purpose Speech Abilities for Large Language Models Using Unpaired Data

no code implementations12 Nov 2023 Yassir Fathullah, Chunyang Wu, Egor Lakomkin, Junteng Jia, Yuan Shangguan, Jay Mahadeokar, Ozlem Kalinli, Christian Fuegen, Mike Seltzer

In this work, we extend the instruction-tuned Llama-2 model with end-to-end general-purpose speech processing and reasoning abilities while maintaining the wide range of LLM capabilities, without using any carefully curated paired data.

Question Answering

Dynamic ASR Pathways: An Adaptive Masking Approach Towards Efficient Pruning of A Multilingual ASR Model

no code implementations22 Sep 2023 Jiamin Xie, Ke Li, Jinxi Guo, Andros Tjandra, Yuan Shangguan, Leda Sari, Chunyang Wu, Junteng Jia, Jay Mahadeokar, Ozlem Kalinli

In this work, we propose the use of an adaptive masking approach in two scenarios for pruning a multilingual ASR model efficiently, each resulting in sparse monolingual models or a sparse multilingual model (named as Dynamic ASR Pathways).

Automatic Speech Recognition Automatic Speech Recognition (ASR) +2

TODM: Train Once Deploy Many Efficient Supernet-Based RNN-T Compression For On-device ASR Models

no code implementations5 Sep 2023 Yuan Shangguan, Haichuan Yang, Danni Li, Chunyang Wu, Yassir Fathullah, Dilin Wang, Ayushi Dalmia, Raghuraman Krishnamoorthi, Ozlem Kalinli, Junteng Jia, Jay Mahadeokar, Xin Lei, Mike Seltzer, Vikas Chandra

Results demonstrate that our TODM Supernet either matches or surpasses the performance of manually tuned models by up to a relative of 3% better in word error rate (WER), while efficiently keeping the cost of training many models at a small constant.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +2

Prompting Large Language Models with Speech Recognition Abilities

no code implementations21 Jul 2023 Yassir Fathullah, Chunyang Wu, Egor Lakomkin, Junteng Jia, Yuan Shangguan, Ke Li, Jinxi Guo, Wenhan Xiong, Jay Mahadeokar, Ozlem Kalinli, Christian Fuegen, Mike Seltzer

Furthermore, we perform ablation studies to investigate whether the LLM can be completely frozen during training to maintain its original capabilities, scaling up the audio encoder, and increasing the audio encoder striding to generate fewer embeddings.

Abstractive Text Summarization Automatic Speech Recognition +3

Towards Selection of Text-to-speech Data to Augment ASR Training

no code implementations30 May 2023 Shuo Liu, Leda Sari, Chunyang Wu, Gil Keren, Yuan Shangguan, Jay Mahadeokar, Ozlem Kalinli

This paper presents a method for selecting appropriate synthetic speech samples from a given large text-to-speech (TTS) dataset as supplementary training data for an automatic speech recognition (ASR) model.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +1

Multi-Head State Space Model for Speech Recognition

no code implementations21 May 2023 Yassir Fathullah, Chunyang Wu, Yuan Shangguan, Junteng Jia, Wenhan Xiong, Jay Mahadeokar, Chunxi Liu, Yangyang Shi, Ozlem Kalinli, Mike Seltzer, Mark J. F. Gales

State space models (SSMs) have recently shown promising results on small-scale sequence and language modelling tasks, rivalling and outperforming many attention-based approaches.

Language Modelling speech-recognition +1

Improving Fast-slow Encoder based Transducer with Streaming Deliberation

no code implementations15 Dec 2022 Ke Li, Jay Mahadeokar, Jinxi Guo, Yangyang Shi, Gil Keren, Ozlem Kalinli, Michael L. Seltzer, Duc Le

Experiments on Librispeech and in-house data show relative WER reductions (WERRs) from 3% to 5% with a slight increase in model size and negligible extra token emission latency compared with fast-slow encoder based transducer.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +2

Anchored Speech Recognition with Neural Transducers

no code implementations20 Oct 2022 Desh Raj, Junteng Jia, Jay Mahadeokar, Chunyang Wu, Niko Moritz, Xiaohui Zhang, Ozlem Kalinli

In this paper, we investigate anchored speech recognition to make neural transducers robust to background speech.

speech-recognition Speech Recognition

An Investigation of Monotonic Transducers for Large-Scale Automatic Speech Recognition

no code implementations19 Apr 2022 Niko Moritz, Frank Seide, Duc Le, Jay Mahadeokar, Christian Fuegen

The two most popular loss functions for streaming end-to-end automatic speech recognition (ASR) are RNN-Transducer (RNN-T) and connectionist temporal classification (CTC).

Automatic Speech Recognition Automatic Speech Recognition (ASR) +2

Federated Domain Adaptation for ASR with Full Self-Supervision

no code implementations30 Mar 2022 Junteng Jia, Jay Mahadeokar, Weiyi Zheng, Yuan Shangguan, Ozlem Kalinli, Frank Seide

Cross-device federated learning (FL) protects user privacy by collaboratively training a model on user devices, therefore eliminating the need for collecting, storing, and manually labeling user data.

Automatic Speech Recognition (ASR) Data Augmentation +2

Dissecting User-Perceived Latency of On-Device E2E Speech Recognition

no code implementations6 Apr 2021 Yuan Shangguan, Rohit Prabhavalkar, Hang Su, Jay Mahadeokar, Yangyang Shi, Jiatong Zhou, Chunyang Wu, Duc Le, Ozlem Kalinli, Christian Fuegen, Michael L. Seltzer

As speech-enabled devices such as smartphones and smart speakers become increasingly ubiquitous, there is growing interest in building automatic speech recognition (ASR) systems that can run directly on-device; end-to-end (E2E) speech recognition models such as recurrent neural network transducers and their variants have recently emerged as prime candidates for this task.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +1

Dynamic Encoder Transducer: A Flexible Solution For Trading Off Accuracy For Latency

no code implementations5 Apr 2021 Yangyang Shi, Varun Nagaraja, Chunyang Wu, Jay Mahadeokar, Duc Le, Rohit Prabhavalkar, Alex Xiao, Ching-Feng Yeh, Julian Chan, Christian Fuegen, Ozlem Kalinli, Michael L. Seltzer

DET gets similar accuracy as a baseline model with better latency on a large in-house data set by assigning a lightweight encoder for the beginning part of one utterance and a full-size encoder for the rest.

speech-recognition Speech Recognition

Memory-efficient Speech Recognition on Smart Devices

no code implementations23 Feb 2021 Ganesh Venkatesh, Alagappan Valliappan, Jay Mahadeokar, Yuan Shangguan, Christian Fuegen, Michael L. Seltzer, Vikas Chandra

Recurrent transducer models have emerged as a promising solution for speech recognition on the current and next generation smart devices.

speech-recognition Speech Recognition

Deep Shallow Fusion for RNN-T Personalization

no code implementations16 Nov 2020 Duc Le, Gil Keren, Julian Chan, Jay Mahadeokar, Christian Fuegen, Michael L. Seltzer

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 last few years due to their simplicity, compactness, and excellent performance on generic transcription tasks.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +1

Alignment Restricted Streaming Recurrent Neural Network Transducer

no code implementations5 Nov 2020 Jay Mahadeokar, Yuan Shangguan, Duc Le, Gil Keren, Hang Su, Thong Le, Ching-Feng Yeh, Christian Fuegen, Michael L. Seltzer

There is a growing interest in the speech community in developing Recurrent Neural Network Transducer (RNN-T) models for automatic speech recognition (ASR) applications.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +2

Improved Neural Language Model Fusion for Streaming Recurrent Neural Network Transducer

no code implementations26 Oct 2020 Suyoun Kim, Yuan Shangguan, Jay Mahadeokar, Antoine Bruguier, Christian Fuegen, Michael L. Seltzer, Duc Le

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 leverage unpaired text data during training.

Language Modelling speech-recognition +1

Contextual RNN-T For Open Domain ASR

no code implementations4 Jun 2020 Mahaveer Jain, Gil Keren, Jay Mahadeokar, Geoffrey Zweig, Florian Metze, Yatharth Saraf

By using an attention model and a biasing model to leverage the contextual metadata that accompanies a video, we observe a relative improvement of about 16% in Word Error Rate on Named Entities (WER-NE) for videos with related metadata.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +2

RNN-T For Latency Controlled ASR With Improved Beam Search

no code implementations5 Nov 2019 Mahaveer Jain, Kjell Schubert, Jay Mahadeokar, Ching-Feng Yeh, Kaustubh Kalgaonkar, Anuroop Sriram, Christian Fuegen, Michael L. Seltzer

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 model, language model, punctuation model, inverse text normalization) into one single model.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +3

Cannot find the paper you are looking for? You can Submit a new open access paper.