36 citations · 149 across the 21 of their papers we have counts for
23 papers
Improving Practical Aspects of End-to-End Multi-Talker Speech Recognition for Online and Offline Scenarios
Aswin Shanmugam Subramanian, Amit Das, Naoyuki Kanda +3
We extend the frameworks of Serialized Output Training (SOT) to address practical needs of both streaming and offline automatic speech recognition (ASR) applications. Our approach…
PHRASED: Phrase Dictionary Biasing for Speech Translation
Peidong Wang, Jian Xue, Rui Zhao +3
Phrases are essential to understand the core concepts in conversations. However, due to their rare occurrence in training data, correct translation of phrases is challenging in spe…
Length Aware Speech Translation for Video Dubbing
Harveen Singh Chadha, Aswin Shanmugam Subramanian, Vikas Joshi +4
In video dubbing, aligning translated audio with the source audio is a significant challenge. Our focus is on achieving this efficiently, tailored for real-time, on-device video du…
Streaming Speaker Change Detection and Gender Classification for Transducer-Based Multi-Talker Speech Translation
Peidong Wang, Naoyuki Kanda, Jian Xue +7
Streaming multi-talker speech translation is a task that involves not only generating accurate and fluent translations with low latency but also recognizing when a speaker change o…
Soft Language Identification for Language-Agnostic Many-to-One End-to-End Speech Translation
Peidong Wang, Jian Xue, Jinyu Li +2
Language-agnostic many-to-one end-to-end speech translation models can convert audio signals from different source languages into text in a target language. These models do not nee…
TS-SEP: Joint Diarization and Separation Conditioned on Estimated Speaker Embeddings
Christoph Boeddeker, Aswin Shanmugam Subramanian, Gordon Wichern +2
Since diarization and source separation of meeting data are closely related tasks, we here propose an approach to perform the two objectives jointly. It builds upon the target-spea…
Tackling the Cocktail Fork Problem for Separation and Transcription of Real-World Soundtracks
Darius Petermann, Gordon Wichern, Aswin Shanmugam Subramanian +2
Emulating the human ability to solve the cocktail party problem, i.e., focus on a source of interest in a complex acoustic scene, is a long standing goal of audio source separation…
Hyperbolic Audio Source Separation
Darius Petermann, Gordon Wichern, Aswin Subramanian +1
We introduce a framework for audio source separation using embeddings on a hyperbolic manifold that compactly represent the hierarchical relationship between sound sources and time…
Reverberation as Supervision for Speech Separation
Rohith Aralikatti, Christoph Boeddeker, Gordon Wichern +2
This paper proposes reverberation as supervision (RAS), a novel unsupervised loss function for single-channel reverberant speech separation. Prior methods for unsupervised separati…
Late Audio-Visual Fusion for In-The-Wild Speaker Diarization
Zexu Pan, Gordon Wichern, François G. Germain +2
Speaker diarization is well studied for constrained audios but little explored for challenging in-the-wild videos, which have more speakers, shorter utterances, and inconsistent on…
SANE-TTS: Stable And Natural End-to-End Multilingual Text-to-Speech
Hyunjae Cho, Wonbin Jung, Junhyeok Lee +1
In this paper, we present SANE-TTS, a stable and natural end-to-end multilingual TTS model. By the difficulty of obtaining multilingual corpus for given speaker, training multiling…
Heterogeneous Target Speech Separation
Efthymios Tzinis, Gordon Wichern, Aswin Subramanian +2
We introduce a new paradigm for single-channel target source separation where the sources of interest can be distinguished using non-mutually exclusive concepts (e.g., loudness, ge…
An Exploration of Self-Supervised Pretrained Representations for End-to-End Speech Recognition
Xuankai Chang, Takashi Maekaku, Pengcheng Guo +8
Self-supervised pretraining on speech data has achieved a lot of progress. High-fidelity representation of the speech signal is learned from a lot of untranscribed data and shows p…
Deep Learning based Multi-Source Localization with Source Splitting and its Effectiveness in Multi-Talker Speech Recognition
Aswin Shanmugam Subramanian, Chao Weng, Shinji Watanabe +2
Multi-source localization is an important and challenging technique for multi-talker conversation analysis. This paper proposes a novel supervised learning method using deep neural…
The 2020 ESPnet update: new features, broadened applications, performance improvements, and future plans
Shinji Watanabe, Florian Boyer, Xuankai Chang +12
This paper describes the recent development of ESPnet (https://github.com/espnet/espnet), an end-to-end speech processing toolkit. This project was initiated in December 2017 to ma…
ESPnet-se: end-to-end speech enhancement and separation toolkit designed for asr integration
Chenda Li, Jing Shi, Wangyou Zhang +8
We present ESPnet-SE, which is designed for the quick development of speech enhancement and speech separation systems in a single framework, along with the optional downstream spee…
Directional ASR: A New Paradigm for E2E Multi-Speaker Speech Recognition with Source Localization
Aswin Shanmugam Subramanian, Chao Weng, Shinji Watanabe +4
This paper proposes a new paradigm for handling far-field multi-speaker data in an end-to-end neural network manner, called directional automatic speech recognition (D-ASR), which…
The JHU Multi-Microphone Multi-Speaker ASR System for the CHiME-6 Challenge
Ashish Arora, Desh Raj, Aswin Shanmugam Subramanian +7
This paper summarizes the JHU team's efforts in tracks 1 and 2 of the CHiME-6 challenge for distant multi-microphone conversational speech diarization and recognition in everyday h…
End-to-End Far-Field Speech Recognition with Unified Dereverberation and Beamforming
Wangyou Zhang, Aswin Shanmugam Subramanian, Xuankai Chang +2
Despite successful applications of end-to-end approaches in multi-channel speech recognition, the performance still degrades severely when the speech is corrupted by reverberation.…
Attention-based ASR with Lightweight and Dynamic Convolutions
Yuya Fujita, Aswin Shanmugam Subramanian, Motoi Omachi +1
End-to-end (E2E) automatic speech recognition (ASR) with sequence-to-sequence models has gained attention because of its simple model training compared with conventional hidden Mar…
An Investigation of End-to-End Multichannel Speech Recognition for Reverberant and Mismatch Conditions
Aswin Shanmugam Subramanian, Xiaofei Wang, Shinji Watanabe +3
Sequence-to-sequence (S2S) modeling is becoming a popular paradigm for automatic speech recognition (ASR) because of its ability to jointly optimize all the conventional ASR compon…
Building state-of-the-art distant speech recognition using the CHiME-4 challenge with a setup of speech enhancement baseline
Szu-Jui Chen, Aswin Shanmugam Subramanian, Hainan Xu +1
This paper describes a new baseline system for automatic speech recognition (ASR) in the CHiME-4 challenge to promote the development of noisy ASR in speech processing communities…
Student-Teacher Learning for BLSTM Mask-based Speech Enhancement
Aswin Shanmugam Subramanian, Szu-Jui Chen, Shinji Watanabe
Spectral mask estimation using bidirectional long short-term memory (BLSTM) neural networks has been widely used in various speech enhancement applications, and it has achieved gre…