1.5k citations · 3k across the 43 of their papers we have counts for
13 papers · 1 filter
Resource-Efficient Adaptation of Speech Foundation Models for Multi-Speaker ASR
Weiqing Wang, Kunal Dhawan, Taejin Park +6
Speech foundation models have achieved state-of-the-art (SoTA) performance across various tasks, such as automatic speech recognition (ASR) in hundreds of languages. However, multi…
Instruction Data Generation and Unsupervised Adaptation for Speech Language Models
Vahid Noroozi, Zhehuai Chen, Somshubra Majumdar +3
In this paper, we propose three methods for generating synthetic samples to train and evaluate multimodal large language models capable of processing both text and speech inputs. A…
Investigating End-to-End ASR Architectures for Long Form Audio Transcription
Nithin Rao Koluguri, Samuel Kriman, Georgy Zelenfroind +5
This paper presents an overview and evaluation of some of the end-to-end ASR models on long-form audios. We study three categories of Automatic Speech Recognition(ASR) models based…
Efficient Sequence Transduction by Jointly Predicting Tokens and Durations
Hainan Xu, Fei Jia, Somshubra Majumdar +3
This paper introduces a novel Token-and-Duration Transducer (TDT) architecture for sequence-to-sequence tasks. TDT extends conventional RNN-Transducer architectures by jointly pred…
Fast Conformer with Linearly Scalable Attention for Efficient Speech Recognition
Dima Rekesh, Nithin Rao Koluguri, Samuel Kriman +8
Conformer-based models have become the dominant end-to-end architecture for speech processing tasks. With the objective of enhancing the conformer architecture for efficient traini…
Multi-blank Transducers for Speech Recognition
Hainan Xu, Fei Jia, Somshubra Majumdar +2
This paper proposes a modification to RNN-Transducer (RNN-T) models for automatic speech recognition (ASR). In standard RNN-T, the emission of a blank symbol consumes exactly one i…
CTC Variations Through New WFST Topologies
Aleksandr Laptev, Somshubra Majumdar, Boris Ginsburg
This paper presents novel Weighted Finite-State Transducer (WFST) topologies to implement Connectionist Temporal Classification (CTC)-like algorithms for automatic speech recogniti…
CarneliNet: Neural Mixture Model for Automatic Speech Recognition
Aleksei Kalinov, Somshubra Majumdar, Jagadeesh Balam +1
End-to-end automatic speech recognition systems have achieved great accuracy by using deeper and deeper models. However, the increased depth comes with a larger receptive field tha…
Citrinet: Closing the Gap between Non-Autoregressive and Autoregressive End-to-End Models for Automatic Speech Recognition
Somshubra Majumdar, Jagadeesh Balam, Oleksii Hrinchuk +3
We propose Citrinet - a new end-to-end convolutional Connectionist Temporal Classification (CTC) based automatic speech recognition (ASR) model. Citrinet is deep residual neural mo…
Improving Noise Robustness of an End-to-End Neural Model for Automatic Speech Recognition
Jagadeesh Balam, Jocelyn Huang, Vitaly Lavrukhin +3
We present our experiments in training robust to noise an end-to-end automatic speech recognition (ASR) model using intensive data augmentation. We explore the efficacy of fine-tun…
MarbleNet: Deep 1D Time-Channel Separable Convolutional Neural Network for Voice Activity Detection
Fei Jia, Somshubra Majumdar, Boris Ginsburg
We present MarbleNet, an end-to-end neural network for Voice Activity Detection (VAD). MarbleNet is a deep residual network composed from blocks of 1D time-channel separable convol…
MatchboxNet: 1D Time-Channel Separable Convolutional Neural Network Architecture for Speech Commands Recognition
Somshubra Majumdar, Boris Ginsburg
We present an MatchboxNet - an end-to-end neural network for speech command recognition. MatchboxNet is a deep residual network composed from blocks of 1D time-channel separable co…
Pathological Voice Classification Using Mel-Cepstrum Vectors and Support Vector Machine
Maryam Pishgar, Fazle Karim, Somshubra Majumdar +1
Vocal disorders have affected several patients all over the world. Due to the inherent difficulty of diagnosing vocal disorders without sophisticated equipment and trained personne…