6 citations · 19 across the 21 of their papers we have counts for
23 papers
How Reliable Are Predicted MOS for Reproducing Human System-Level Preferences in Speech Enhancement?
Nahomi Kusunoki, Tsubasa Ochiai, Naohiro Tawara +4
We investigate whether predicted Mean Opinion Scores (MOS) can reliably support system-level comparisons of speech enhancement (SE) methods by introducing system-level preference a…
Improving Predicted MOS Scores, Not Perceived Quality: Multi-Predictor Test-Time Optimization of Enhanced Speech
Tsubasa Ochiai, Marc Delcroix, Nahomi Kusunoki +5
Non-intrusive MOS predictors are widely used instead of subjective listening tests to evaluate and rank speech enhancement (SE) systems. If they accurately reflect perceived qualit…
Speaker-Distinguishable CTC: Learning Speaker Distinction Using CTC for Multi-Talker Speech Recognition
Asahi Sakuma, Hiroaki Sato, Ryuga Sugano +3
This paper presents a novel framework for multi-talker automatic speech recognition without the need for auxiliary information. Serialized Output Training (SOT), a widely used appr…
A Comparative Study on Positional Encoding for Time-frequency Domain Dual-path Transformer-based Source Separation Models
Kohei Saijo, Tetsuji Ogawa
In this study, we investigate the impact of positional encoding (PE) on source separation performance and the generalization ability to long sequences (length extrapolation) in Tra…
End-to-End Speech Recognition with Pre-trained Masked Language Model
Yosuke Higuchi, Tetsuji Ogawa, Tetsunori Kobayashi +1
We present a novel approach to end-to-end automatic speech recognition (ASR) that utilizes pre-trained masked language models (LMs) to facilitate the extraction of linguistic infor…
A Single Speech Enhancement Model Unifying Dereverberation, Denoising, Speaker Counting, Separation, and Extraction
Kohei Saijo, Wangyou Zhang, Zhong-Qiu Wang +3
We propose a multi-task universal speech enhancement (MUSE) model that can perform five speech enhancement (SE) tasks: dereverberation, denoising, speech separation (SS), target sp…
Mask-CTC-based Encoder Pre-training for Streaming End-to-End Speech Recognition
Huaibo Zhao, Yosuke Higuchi, Yusuke Kida +2
Achieving high accuracy with low latency has always been a challenge in streaming end-to-end automatic speech recognition (ASR) systems. By attending to more future contexts, a str…
Harnessing the Zero-Shot Power of Instruction-Tuned Large Language Model in End-to-End Speech Recognition
Yosuke Higuchi, Tetsuji Ogawa, Tetsunori Kobayashi
We propose to utilize an instruction-tuned large language model (LLM) for guiding the text generation process in automatic speech recognition (ASR). Modern large language models (L…
Remixing-based Unsupervised Source Separation from Scratch
Kohei Saijo, Tetsuji Ogawa
We propose an unsupervised approach for training separation models from scratch using RemixIT and Self-Remixing, which are recently proposed self-supervised learning methods for re…
Neural Diarization with Non-autoregressive Intermediate Attractors
Yusuke Fujita, Tatsuya Komatsu, Robin Scheibler +2
End-to-end neural diarization (EEND) with encoder-decoder-based attractors (EDA) is a promising method to handle the whole speaker diarization problem simultaneously with a single…
Deep Multi-stream Network for Video-based Calving Sign Detection
Ryosuke Hyodo, Teppei Nakano, Tetsuji Ogawa
We have designed a deep multi-stream network for automatically detecting calving signs from video. Calving sign detection from a camera, which is a non-contact sensor, is expected…
Video Surveillance System Incorporating Expert Decision-making Process: A Case Study on Detecting Calving Signs in Cattle
Ryosuke Hyodo, Susumu Saito, Teppei Nakano +3
Through a user study in the field of livestock farming, we verify the effectiveness of an XAI framework for video surveillance systems. The systems can be made interpretable by inc…
Conversation-oriented ASR with multi-look-ahead CBS architecture
Huaibo Zhao, Shinya Fujie, Tetsuji Ogawa +3
During conversations, humans are capable of inferring the intention of the speaker at any point of the speech to prepare the following action promptly. Such ability is also the key…
Self-Remixing: Unsupervised Speech Separation via Separation and Remixing
Kohei Saijo, Tetsuji Ogawa
We present Self-Remixing, a novel self-supervised speech separation method, which refines a pre-trained separation model in an unsupervised manner. The proposed method consists of…
InterMPL: Momentum Pseudo-Labeling with Intermediate CTC Loss
Yosuke Higuchi, Tetsuji Ogawa, Tetsunori Kobayashi +1
This paper presents InterMPL, a semi-supervised learning method of end-to-end automatic speech recognition (ASR) that performs pseudo-labeling (PL) with intermediate supervision. M…
BECTRA: Transducer-based End-to-End ASR with BERT-Enhanced Encoder
Yosuke Higuchi, Tetsuji Ogawa, Tetsunori Kobayashi +1
We present BERT-CTC-Transducer (BECTRA), a novel end-to-end automatic speech recognition (E2E-ASR) model formulated by the transducer with a BERT-enhanced encoder. Integrating a la…
BERT Meets CTC: New Formulation of End-to-End Speech Recognition with Pre-trained Masked Language Model
Yosuke Higuchi, Brian Yan, Siddhant Arora +3
This paper presents BERT-CTC, a novel formulation of end-to-end speech recognition that adapts BERT for connectionist temporal classification (CTC). Our formulation relaxes the con…
Remix-cycle-consistent Learning on Adversarially Learned Separator for Accurate and Stable Unsupervised Speech Separation
Kohei Saijo, Tetsuji Ogawa
A new learning algorithm for speech separation networks is designed to explicitly reduce residual noise and artifacts in the separated signal in an unsupervised manner. Generative…
An Investigation of Enhancing CTC Model for Triggered Attention-based Streaming ASR
Huaibo Zhao, Yosuke Higuchi, Tetsuji Ogawa +1
In the present paper, an attempt is made to combine Mask-CTC and the triggered attention mechanism to construct a streaming end-to-end automatic speech recognition (ASR) system tha…
Hierarchical Conditional End-to-End ASR with CTC and Multi-Granular Subword Units
Yosuke Higuchi, Keita Karube, Tetsuji Ogawa +1
In end-to-end automatic speech recognition (ASR), a model is expected to implicitly learn representations suitable for recognizing a word-level sequence. However, the huge abstract…
Exploring Effectiveness of Inter-Microtask Qualification Tests in Crowdsourcing
Masaya Morinaga, Susumu Saito, Teppei Nakano +2
Qualification tests in crowdsourcing are often used to pre-filter workers by measuring their ability in executing microtasks.While creating qualification tests for each task type i…
Improved Mask-CTC for Non-Autoregressive End-to-End ASR
Yosuke Higuchi, Hirofumi Inaguma, Shinji Watanabe +2
For real-world deployment of automatic speech recognition (ASR), the system is desired to be capable of fast inference while relieving the requirement of computational resources. T…
Mask CTC: Non-Autoregressive End-to-End ASR with CTC and Mask Predict
Yosuke Higuchi, Shinji Watanabe, Nanxin Chen +2
We present Mask CTC, a novel non-autoregressive end-to-end automatic speech recognition (ASR) framework, which generates a sequence by refining outputs of the connectionist tempora…