996 citations · 2.4k across the 62 of their papers we have counts for
31 papers · 1 filter
Fast Context-Biasing for CTC and Transducer ASR models with CTC-based Word Spotter
Andrei Andrusenko, Aleksandr Laptev, Vladimir Bataev +2
Accurate recognition of rare and new words remains a pressing problem for contextualized Automatic Speech Recognition (ASR) systems. Most context-biasing methods involve modificati…
Label-Looping: Highly Efficient Decoding for Transducers
Vladimir Bataev, Hainan Xu, Daniel Galvez +2
This paper introduces a highly efficient greedy decoding algorithm for Transducer-based speech recognition models. We redesign the standard nested-loop design for RNN-T decoding, s…
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…
Confidence-based Ensembles of End-to-End Speech Recognition Models
Igor Gitman, Vitaly Lavrukhin, Aleksandr Laptev +1
The number of end-to-end speech recognition models grows every year. These models are often adapted to new domains or languages resulting in a proliferation of expert systems that…
Unified model for code-switching speech recognition and language identification based on a concatenated tokenizer
Kunal Dhawan, Dima Rekesh, Boris Ginsburg
Code-Switching (CS) multilingual Automatic Speech Recognition (ASR) models can transcribe speech containing two or more alternating languages during a conversation. This paper prop…
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…
Powerful and Extensible WFST Framework for RNN-Transducer Losses
Aleksandr Laptev, Vladimir Bataev, Igor Gitman +1
This paper presents a framework based on Weighted Finite-State Transducers (WFST) to simplify the development of modifications for RNN-Transducer (RNN-T) loss. Existing implementat…
Text-only domain adaptation for end-to-end ASR using integrated text-to-mel-spectrogram generator
Vladimir Bataev, Roman Korostik, Evgeny Shabalin +2
We propose an end-to-end Automatic Speech Recognition (ASR) system that can be trained on transcribed speech data, text-only data, or a mixture of both. The proposed model uses an…
Fast Entropy-Based Methods of Word-Level Confidence Estimation for End-To-End Automatic Speech Recognition
Aleksandr Laptev, Boris Ginsburg
This paper presents a class of new fast non-trainable entropy-based confidence estimation methods for automatic speech recognition. We show how per-frame entropy values can be norm…
Accidental Learners: Spoken Language Identification in Multilingual Self-Supervised Models
Travis M. Bartley, Fei Jia, Krishna C. Puvvada +2
In this paper, we extend previous self-supervised approaches for language identification by experimenting with Conformer based architecture in a multilingual pre-training paradigm.…
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…
Adapter-Based Extension of Multi-Speaker Text-to-Speech Model for New Speakers
Cheng-Ping Hsieh, Subhankar Ghosh, Boris Ginsburg
Fine-tuning is a popular method for adapting text-to-speech (TTS) models to new speakers. However this approach has some challenges. Usually fine-tuning requires several hours of h…
A Compact End-to-End Model with Local and Global Context for Spoken Language Identification
Fei Jia, Nithin Rao Koluguri, Jagadeesh Balam +1
We introduce TitaNet-LID, a compact end-to-end neural network for Spoken Language Identification (LID) that is based on the ContextNet architecture. TitaNet-LID employs 1D depth-wi…
Multi-scale Speaker Diarization with Dynamic Scale Weighting
Tae Jin Park, Nithin Rao Koluguri, Jagadeesh Balam +1
Speaker diarization systems are challenged by a trade-off between the temporal resolution and the fidelity of the speaker representation. By obtaining a superior temporal resolutio…
Mixer-TTS: non-autoregressive, fast and compact text-to-speech model conditioned on language model embeddings
Oktai Tatanov, Stanislav Beliaev, Boris Ginsburg
This paper describes Mixer-TTS, a non-autoregressive model for mel-spectrogram generation. The model is based on the MLP-Mixer architecture adapted for speech synthesis. The basic…
TitaNet: Neural Model for speaker representation with 1D Depth-wise separable convolutions and global context
Nithin Rao Koluguri, Taejin Park, Boris Ginsburg
In this paper, we propose TitaNet, a novel neural network architecture for extracting speaker representations. We employ 1D depth-wise separable convolutions with Squeeze-and-Excit…
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…
TalkNet 2: Non-Autoregressive Depth-Wise Separable Convolutional Model for Speech Synthesis with Explicit Pitch and Duration Prediction
Stanislav Beliaev, Boris Ginsburg
We propose TalkNet, a non-autoregressive convolutional neural model for speech synthesis with explicit pitch and duration prediction. The model consists of three feed-forward convo…
A Toolbox for Construction and Analysis of Speech Datasets
Evelina Bakhturina, Vitaly Lavrukhin, Boris Ginsburg
Automatic Speech Recognition and Text-to-Speech systems are primarily trained in a supervised fashion and require high-quality, accurately labeled speech datasets. In this work, we…
Hi-Fi Multi-Speaker English TTS Dataset
Evelina Bakhturina, Vitaly Lavrukhin, Boris Ginsburg +1
This paper introduces a new multi-speaker English dataset for training text-to-speech models. The dataset is based on LibriVox audiobooks and Project Gutenberg texts, both in the p…
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…