research
∙
09/19/2023
Discrete Audio Representation as an Alternative to Mel-Spectrograms for Speaker and Speech Recognition
Discrete audio representation, aka audio tokenization, has seen renewed ...
share
research
∙
09/18/2023
Investigating End-to-End ASR Architectures for Long Form Audio Transcription
This paper presents an overview and evaluation of some of the end-to-end...
research
∙
07/13/2023
Leveraging Pretrained ASR Encoders for Effective and Efficient End-to-End Speech Intent Classification and Slot Filling
We study speech intent classification and slot filling (SICSF) by propos...
research
∙
06/27/2023
Confidence-based Ensembles of End-to-End Speech Recognition Models
The number of end-to-end speech recognition models grows every year. The...
research
∙
06/14/2023
Towards training Bilingual and Code-Switched Speech Recognition models from Monolingual data sources
Multilingual Automatic Speech Recognition (ASR) models are capable of tr...
research
∙
06/04/2023
SpellMapper: A non-autoregressive neural spellchecker for ASR customization with candidate retrieval based on n-gram mappings
Contextual spelling correction models are an alternative to shallow fusi...
research
∙
05/08/2023
Fast Conformer with Linearly Scalable Attention for Efficient Speech Recognition
Conformer-based models have become the most dominant end-to-end architec...
research
∙
04/13/2023
Efficient Sequence Transduction by Jointly Predicting Tokens and Durations
This paper introduces a novel Token-and-Duration Transducer (TDT) archit...
research
∙
03/18/2023
Powerful and Extensible WFST Framework for RNN-Transducer Losses
This paper presents a framework based on Weighted Finite-State Transduce...
research
∙
02/27/2023
Text-only domain adaptation for end-to-end ASR using integrated text-to-mel-spectrogram generator
We propose an end-to-end ASR system that can be trained on transcribed s...
research
∙
02/16/2023
ACE-VC: Adaptive and Controllable Voice Conversion using Explicitly Disentangled Self-supervised Speech Representations
In this work, we propose a zero-shot voice conversion method using speec...
research
∙
12/16/2022
Fast Entropy-Based Methods of Word-Level Confidence Estimation for End-To-End Automatic Speech Recognition
This paper presents a class of new fast non-trainable entropy-based conf...
research
∙
11/09/2022
Accidental Learners: Spoken Language Identification in Multilingual Self-Supervised Models
In this paper, we extend previous self-supervised approaches for languag...
research
∙
11/04/2022
Multi-blank Transducers for Speech Recognition
This paper proposes a modification to RNN-Transducer (RNN-T) models for ...
research
∙
11/01/2022
Adapter-Based Extension of Multi-Speaker Text-to-Speech Model for New Speakers
Fine-tuning is a popular method for adapting text-to-speech (TTS) models...
research
∙
10/27/2022
AmberNet: A Compact End-to-End Model for Spoken Language Identification
We present AmberNet, a compact end-to-end neural network for Spoken Lang...
research
∙
10/06/2022
Damage Control During Domain Adaptation for Transducer Based Automatic Speech Recognition
Automatic speech recognition models are often adapted to improve their a...
research
∙
07/29/2022
Thutmose Tagger: Single-pass neural model for Inverse Text Normalization
Inverse text normalization (ITN) is an essential post-processing step in...
research
∙
06/09/2022
BigVGAN: A Universal Neural Vocoder with Large-Scale Training
Despite recent progress in generative adversarial network(GAN)-based voc...
research
∙
03/30/2022
Multi-scale Speaker Diarization with Dynamic Scale Weighting
Speaker diarization systems are challenged by a trade-off between the te...
research
∙
10/12/2021
Adapting TTS models For New Speakers using Transfer Learning
Training neural text-to-speech (TTS) models for a new speaker typically ...
research
∙
10/08/2021
TitaNet: Neural Model for speaker representation with 1D Depth-wise separable convolutions and global context
In this paper, we propose TitaNet, a novel neural network architecture f...
research
∙
10/06/2021
CTC Variations Through New WFST Topologies
This paper presents novel Weighted Finite-State Transducer (WFST) topolo...
research
∙
08/23/2021
A Unified Transformer-based Framework for Duplex Text Normalization
Text normalization (TN) and inverse text normalization (ITN) are essenti...
research
∙
07/22/2021
CarneliNet: Neural Mixture Model for Automatic Speech Recognition
End-to-end automatic speech recognition systems have achieved great accu...
research
∙
05/17/2021
SGD-QA: Fast Schema-Guided Dialogue State Tracking for Unseen Services
Dialogue state tracking is an essential part of goal-oriented dialogue s...
research
∙
04/16/2021
TalkNet 2: Non-Autoregressive Depth-Wise Separable Convolutional Model for Speech Synthesis with Explicit Pitch and Duration Prediction
We propose TalkNet, a non-autoregressive convolutional neural model for ...
research
∙
04/11/2021
NeMo Inverse Text Normalization: From Development To Production
Inverse text normalization (ITN) converts spoken-domain automatic speech...
research
∙
04/11/2021
NeMo Toolbox for Speech Dataset Construction
In this paper, we introduce a new toolbox for constructing speech datase...
research
∙
04/05/2021
SPGISpeech: 5,000 hours of transcribed financial audio for fully formatted end-to-end speech recognition
In the English speech-to-text (STT) machine learning task, acoustic mode...
research
∙
10/26/2020
MarbleNet: Deep 1D Time-Channel Separable Convolutional Neural Network for Voice Activity Detection
We present MarbleNet, an end-to-end neural network for Voice Activity De...
research
∙
07/18/2020
On regularization of gradient descent, layer imbalance and flat minima
We analyze the training dynamics for deep linear networks using a new me...
research
∙
10/23/2019
Correction of Automatic Speech Recognition with Transformer Sequence-to-sequence Model
In this work, we introduce a simple yet efficient post-processing model ...
research
∙
09/14/2019
NeMo: a toolkit for building AI applications using Neural Modules
NeMo (Neural Modules) is a Python framework-agnostic toolkit for creatin...
research
∙
05/27/2019
Stochastic Gradient Methods with Layer-wise Adaptive Moments for Training of Deep Networks
We propose NovoGrad, a first-order stochastic gradient method with layer...
research
∙
04/05/2019
Jasper: An End-to-End Convolutional Neural Acoustic Model
In this paper, we report state-of-the-art results on LibriSpeech among e...
research
∙
11/02/2018
Training Neural Speech Recognition Systems with Synthetic Speech Augmentation
Building an accurate automatic speech recognition (ASR) system requires ...
research
∙
05/25/2018
OpenSeq2Seq: extensible toolkit for distributed and mixed precision training of sequence-to-sequence models
We present OpenSeq2Seq -- an open-source toolkit for training sequence-t...
research
∙
10/10/2017
Mixed Precision Training
Deep neural networks have enabled progress in a wide variety of applicat...
research
∙
09/24/2017
Comparison of Batch Normalization and Weight Normalization Algorithms for the Large-scale Image Classification
Batch normalization (BN) has become a de facto standard for training dee...
research
∙
08/13/2017
Large Batch Training of Convolutional Networks
A common way to speed up training of large convolutional networks is to ...
research
∙
08/05/2017
Training Deep AutoEncoders for Collaborative Filtering
This paper proposes a novel model for the rating prediction task in reco...
research
∙
03/31/2017
Factorization tricks for LSTM networks
We present two simple ways of reducing the number of parameters and acce...
research
∙
09/02/2016