Mt RNN

Recurrent Neural Network Transducers (RNN-Ts) are a prominent architecture for end-to-end speech recognition, aiming to improve accuracy and efficiency in streaming applications. Current research focuses on optimizing RNN-T models through techniques like efficient decoding algorithms (e.g., greedy decoding, beam search), model compression (e.g., weight binarization), and addressing challenges such as training data imperfections and robustness to adversarial attacks. These advancements are significant for improving the speed, memory efficiency, and accuracy of speech recognition systems, impacting both research in automatic speech recognition and the development of real-world applications like voice assistants and voice search.

Papers

October 29, 2022

Accelerating RNN-T Training and Inference Using CTC guidance
Yongqiang Wang, Zhehuai Chen, Chengjian Zheng, Yu Zhang, Wei Han, Parisa Haghani
Scientific Inference Connectionist Temporal Classification Mt RNN Recurrent Neural Network Transducer RNN T Training RNN Inference

September 29, 2022

ConvRNN-T: Convolutional Augmented Recurrent Neural Network Transducers for Streaming Speech Recognition
Martin Radfar, Rohit Barnwal, Rupak Vignesh Swaminathan, Feng-Ju Chang, Grant P. Strimel, Nathan Susanj, Athanasios Mouchtaris
Speech Recognition Mt RNN Recurrent Neural Network Transducer

September 13, 2022

Streaming End-to-End Multilingual Speech Recognition with Joint Language Identification
Chao Zhang, Bo Li, Tara Sainath, Trevor Strohman, Sepand Mavandadi, Shuo-yiin Chang, Parisa Haghani
End to End Language Identification Mt RNN Multilingual Speech Recurrent Neural Network Transducer Multilingual Speech Model

June 29, 2022

On the Prediction Network Architecture in RNN-T for ASR
Dario Albesano, Jesús Andrés-Ferrer, Nicola Ferri, Puming Zhan
Automatic Speech Recognition LSTM Network Mt RNN Conformer Encoder RNN T Model

June 28, 2022

Learning State Machines to Monitor and Detect Anomalies on a Kubernetes Cluster
Clinton Cao, Agathe Blaise, Sicco Verwer, Filippo Rebecchi
Unlabeled Anomaly Mt RNN Anomalous Behavior Cloud Environment Kubernetes Cluster State Machine

June 23, 2022

Pruned RNN-T for fast, memory-efficient ASR training
Fangjun Kuang, Liyong Guo, Wei Kang, Long Lin, Mingshuang Luo, Zengwei Yao, Daniel Povey
Neural Network Mt RNN RNN Transducer Memory Efficient Training RNN T Loss

June 16, 2022

Accelerating Inference and Language Model Fusion of Recurrent Neural Network Transducers via End-to-End 4-bit Quantization
Andrea Fasoli, Chia-Yu Chen, Mauricio Serrano, Swagath Venkataramani, George Saon, Xiaodong Cui, Brian Kingsbury, Kailash Gopalakrishnan
Language Model Quantization Technique Mt RNN Bit Quantization RNN T Model

May 10, 2022

Separator-Transducer-Segmenter: Streaming Recognition and Segmentation of Multi-party Speech
Ilya Sklyar, Anna Piunova, Christian Osendorfer
Speech Recognition Segmentation Based Approach Speech Separation Multi Party Mt RNN Recurrent Neural Network Transducer

April 19, 2022

An Investigation of Monotonic Transducers for Large-Scale Automatic Speech Recognition
Niko Moritz, Frank Seide, Duc Le, Jay Mahadeokar, Christian Fuegen
Automatic Speech Recognition Connectionist Temporal Classification Mt RNN RNN Transducer Monotonic Neural Network

March 31, 2022

February 21, 2022

Adaptive Discounting of Implicit Language Models in RNN-Transducers
Vinit Unni, Shreya Khare, Ashish Mittal, Preethi Jyothi, Sunita Sarawagi, Samarth Bharadwaj
Language Model Mt RNN RNN Architecture RNN Transducer

February 8, 2022

RNN Transducers for Nested Named Entity Recognition with constraints on alignment for long sequences
Hagen Soltau, Izhak Shafran, Mingqiu Wang, Laurent El Shafey
Alignment Problem Long Sequence Participation Constraint Sequence to Sequence Model Mt RNN RNN Transducer Nested Named Entity Recognition

January 25, 2022

Improving the fusion of acoustic and text representations in RNN-T
Chao Zhang, Bo Li, Zhiyun Lu, Tara N. Sainath, Shuo-yiin Chang
Hybrid Fusion Text Representation Multilingual Automatic Speech Recognition Speech Encoder Mt RNN Recurrent Neural Network Transducer RNN T Training

January 13, 2022

Recognizing semantic relation in sentence pairs using Tree-RNNs and Typed dependencies
Jeena Kleenankandy, K A Abdul Nazeer
Mt RNN Sentence Pair Semantic Textual Relatedness RNN T Training Tree LSTMs

January 10, 2022

A Likelihood Ratio based Domain Adaptation Method for E2E Models
Chhavi Choudhury, Ankur Gandhe, Xiaohan Ding, Ivan Bulyko
Domain Adaptation Contextual Biasing Speech Recognition Model Mt RNN End 2 End Recurrent Neural Network Transducer Likelihood Ratio

December 19, 2021

Multi-turn RNN-T for streaming recognition of multi-party speech
Ilya Sklyar, Anna Piunova, Xianrui Zheng, Yulan Liu
Automatic Speech Recognition Recognition Rate Multi Party Multi Speaker Mt RNN Multi Speaker Automatic Speech Recognition

December 1, 2021

November 19, 2021

A comparison of streaming models and data augmentation methods for robust speech recognition
Jiyeon Kim, Mehul Kumar, Dhananjaya Gowda, Abhinav Garg, Chanwoo Kim
Speech Recognition Consistent Comparison Data Augmentation Method Mt RNN Recurrent Neural Network Transducer Streaming Model RNN T Model

Mt RNN

Papers

Accelerating RNN-T Training and Inference Using CTC guidance

ConvRNN-T: Convolutional Augmented Recurrent Neural Network Transducers for Streaming Speech Recognition

Streaming End-to-End Multilingual Speech Recognition with Joint Language Identification

On the Prediction Network Architecture in RNN-T for ASR

Learning State Machines to Monitor and Detect Anomalies on a Kubernetes Cluster

Pruned RNN-T for fast, memory-efficient ASR training

Accelerating Inference and Language Model Fusion of Recurrent Neural Network Transducers via End-to-End 4-bit Quantization

Separator-Transducer-Segmenter: Streaming Recognition and Segmentation of Multi-party Speech

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

CTA-RNN: Channel and Temporal-wise Attention RNN Leveraging Pre-trained ASR Embeddings for Speech Emotion Recognition

An Empirical Study of Language Model Integration for Transducer based Speech Recognition

Adaptive Discounting of Implicit Language Models in RNN-Transducers

RNN Transducers for Nested Named Entity Recognition with constraints on alignment for long sequences

Improving the fusion of acoustic and text representations in RNN-T

Recognizing semantic relation in sentence pairs using Tree-RNNs and Typed dependencies

A Likelihood Ratio based Domain Adaptation Method for E2E Models

Multi-turn RNN-T for streaming recognition of multi-party speech

Investigation of Training Label Error Impact on RNN-T

Deliberation of Streaming RNN-Transducer by Non-autoregressive Decoding

A comparison of streaming models and data augmentation methods for robust speech recognition