120 citations · 347 across the 47 of their papers we have counts for
49 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…
Ontology-based Target Sound Extraction
Carlos Hernandez-Olivan, Marc Delcroix, Tsubasa Ochiai +2
Target sound extraction (TSE) aims to isolate a sound source of interest from a mixture, given a semantic query. Existing TSE systems are conditioned on fixed class representations…
Frontend Token Enhancement for Token-Based Speech Recognition
Takanori Ashihara, Shota Horiguchi, Kohei Matsuura +2
Discretized representations of speech signals are efficient alternatives to continuous features for various speech applications, including automatic speech recognition (ASR) and sp…
MOVER: Combining Multiple Meeting Recognition Systems
Naoyuki Kamo, Tsubasa Ochiai, Marc Delcroix +1
In this paper, we propose Meeting recognizer Output Voting Error Reduction (MOVER), a novel system combination method for meeting recognition tasks. Although there are methods to c…
Generic Speech Enhancement with Self-Supervised Representation Space Loss
Hiroshi Sato, Tsubasa Ochiai, Marc Delcroix +3
Single-channel speech enhancement is utilized in various tasks to mitigate the effect of interfering signals. Conventionally, to ensure the speech enhancement performs optimally, t…
TS-SUPERB: A Target Speech Processing Benchmark for Speech Self-Supervised Learning Models
Junyi Peng, Takanori Ashihara, Marc Delcroix +4
Self-supervised learning (SSL) models have significantly advanced speech processing tasks, and several benchmarks have been proposed to validate their effectiveness. However, previ…
Microphone Array Geometry Independent Multi-Talker Distant ASR: NTT System for the DASR Task of the CHiME-8 Challenge
Naoyuki Kamo, Naohiro Tawara, Atsushi Ando +15
In this paper, we introduce a multi-talker distant automatic speech recognition (DASR) system we designed for the DASR task 1 of the CHiME-8 challenge. Our system performs speaker…
Microphone Array Signal Processing and Deep Learning for Speech Enhancement
Reinhold Haeb-Umbach, Tomohiro Nakatani, Marc Delcroix +2
Multi-channel acoustic signal processing is a well-established and powerful tool to exploit the spatial diversity between a target signal and non-target or noise sources for signal…
Investigation of Speaker Representation for Target-Speaker Speech Processing
Takanori Ashihara, Takafumi Moriya, Shota Horiguchi +5
Target-speaker speech processing (TS) tasks, such as target-speaker automatic speech recognition (TS-ASR), target speech extraction (TSE), and personal voice activity detection (p-…
SoundBeam meets M2D: Target Sound Extraction with Audio Foundation Model
Carlos Hernandez-Olivan, Marc Delcroix, Tsubasa Ochiai +4
Target sound extraction (TSE) consists of isolating a desired sound from a mixture of arbitrary sounds using clues to identify it. A TSE system requires solving two problems at onc…
NTT Multi-Speaker ASR System for the DASR Task of CHiME-8 Challenge
Naoyuki Kamo, Naohiro Tawara, Atsushi Ando +15
We present a distant automatic speech recognition (DASR) system developed for the CHiME-8 DASR track. It consists of a diarization first pipeline. For diarization, we use end-to-en…
Interaural time difference loss for binaural target sound extraction
Carlos Hernandez-Olivan, Marc Delcroix, Tsubasa Ochiai +3
Binaural target sound extraction (TSE) aims to extract a desired sound from a binaural mixture of arbitrary sounds while preserving the spatial cues of the desired sound. Indeed, f…
SpeakerBeam-SS: Real-time Target Speaker Extraction with Lightweight Conv-TasNet and State Space Modeling
Hiroshi Sato, Takafumi Moriya, Masato Mimura +6
Real-time target speaker extraction (TSE) is intended to extract the desired speaker's voice from the observed mixture of multiple speakers in a streaming manner. Implementing real…
Rethinking Processing Distortions: Disentangling the Impact of Speech Enhancement Errors on Speech Recognition Performance
Tsubasa Ochiai, Kazuma Iwamoto, Marc Delcroix +4
It is challenging to improve automatic speech recognition (ASR) performance in noisy conditions with a single-channel speech enhancement (SE) front-end. This is generally attribute…
Probing Self-supervised Learning Models with Target Speech Extraction
Junyi Peng, Marc Delcroix, Tsubasa Ochiai +4
Large-scale pre-trained self-supervised learning (SSL) models have shown remarkable advancements in speech-related tasks. However, the utilization of these models in complex multi-…
Target Speech Extraction with Pre-trained Self-supervised Learning Models
Junyi Peng, Marc Delcroix, Tsubasa Ochiai +3
Pre-trained self-supervised learning (SSL) models have achieved remarkable success in various speech tasks. However, their potential in target speech extraction (TSE) has not been…
Array Geometry-Robust Attention-Based Neural Beamformer for Moving Speakers
Marvin Tammen, Tsubasa Ochiai, Marc Delcroix +3
Although mask-based beamforming is a powerful speech enhancement approach, it often requires manual parameter tuning to handle moving speakers. Recently, this approach was augmente…
How does end-to-end speech recognition training impact speech enhancement artifacts?
Kazuma Iwamoto, Tsubasa Ochiai, Marc Delcroix +4
Jointly training a speech enhancement (SE) front-end and an automatic speech recognition (ASR) back-end has been investigated as a way to mitigate the influence of \emph{processing…
Neural network-based virtual microphone estimation with virtual microphone and beamformer-level multi-task loss
Hanako Segawa, Tsubasa Ochiai, Marc Delcroix +5
Array processing performance depends on the number of microphones available. Virtual microphone estimation (VME) has been proposed to increase the number of microphone signals arti…
Knowledge Distillation for Neural Transducer-based Target-Speaker ASR: Exploiting Parallel Mixture/Single-Talker Speech Data
Takafumi Moriya, Hiroshi Sato, Tsubasa Ochiai +7
Neural transducer (RNNT)-based target-speaker speech recognition (TS-RNNT) directly transcribes a target speaker's voice from a multi-talker mixture. It is a promising approach for…
Downstream Task Agnostic Speech Enhancement with Self-Supervised Representation Loss
Hiroshi Sato, Ryo Masumura, Tsubasa Ochiai +8
Self-supervised learning (SSL) is the latest breakthrough in speech processing, especially for label-scarce downstream tasks by leveraging massive unlabeled audio data. The noise r…
Neural Target Speech Extraction: An Overview
Katerina Zmolikova, Marc Delcroix, Tsubasa Ochiai +3
Humans can listen to a target speaker even in challenging acoustic conditions that have noise, reverberation, and interfering speakers. This phenomenon is known as the cocktail-par…
Streaming Target-Speaker ASR with Neural Transducer
Takafumi Moriya, Hiroshi Sato, Tsubasa Ochiai +2
Although recent advances in deep learning technology have boosted automatic speech recognition (ASR) performance in the single-talker case, it remains difficult to recognize multi-…