28 citations · 44 across the 25 of their papers we have counts for
25 papers
All-in-One ASR: Unifying Encoder-Decoder Models of CTC, Attention, and Transducer in Dual-Mode ASR
Takafumi Moriya, Masato Mimura, Tomohiro Tanaka +3
This paper proposes a unified framework, All-in-One ASR, that allows a single model to support multiple automatic speech recognition (ASR) paradigms, including connectionist tempor…
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…
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…
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-…
Guided Speaker Embedding
Shota Horiguchi, Takafumi Moriya, Atsushi Ando +4
This paper proposes a guided speaker embedding extraction system, which extracts speaker embeddings of the target speaker using speech activities of target and interference speaker…
Boosting Hybrid Autoregressive Transducer-based ASR with Internal Acoustic Model Training and Dual Blank Thresholding
Takafumi Moriya, Takanori Ashihara, Masato Mimura +4
A hybrid autoregressive transducer (HAT) is a variant of neural transducer that models blank and non-blank posterior distributions separately. In this paper, we propose a novel int…
Alignment-Free Training for Transducer-based Multi-Talker ASR
Takafumi Moriya, Shota Horiguchi, Marc Delcroix +5
Extending the RNN Transducer (RNNT) to recognize multi-talker speech is essential for wider automatic speech recognition (ASR) applications. Multi-talker RNNT (MT-RNNT) aims to ach…
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…
Recursive Attentive Pooling for Extracting Speaker Embeddings from Multi-Speaker Recordings
Shota Horiguchi, Atsushi Ando, Takafumi Moriya +4
This paper proposes a method for extracting speaker embedding for each speaker from a variable-length recording containing multiple speakers. Speaker embeddings are crucial not onl…
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…
Noise-robust zero-shot text-to-speech synthesis conditioned on self-supervised speech-representation model with adapters
Kenichi Fujita, Hiroshi Sato, Takanori Ashihara +4
The zero-shot text-to-speech (TTS) method, based on speaker embeddings extracted from reference speech using self-supervised learning (SSL) speech representations, can reproduce sp…
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…
End-to-End Joint Target and Non-Target Speakers ASR
Ryo Masumura, Naoki Makishima, Taiga Yamane +12
This paper proposes a novel automatic speech recognition (ASR) system that can transcribe individual speaker's speech while identifying whether they are target or non-target speake…
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…
Improving Scheduled Sampling for Neural Transducer-based ASR
Takafumi Moriya, Takanori Ashihara, Hiroshi Sato +3
The recurrent neural network-transducer (RNNT) is a promising approach for automatic speech recognition (ASR) with the introduction of a prediction network that autoregressively co…
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…
On the Use of Modality-Specific Large-Scale Pre-Trained Encoders for Multimodal Sentiment Analysis
Atsushi Ando, Ryo Masumura, Akihiko Takashima +6
This paper investigates the effectiveness and implementation of modality-specific large-scale pre-trained encoders for multimodal sentiment analysis~(MSA). Although the effectivene…
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-…
Strategies to Improve Robustness of Target Speech Extraction to Enrollment Variations
Hiroshi Sato, Tsubasa Ochiai, Marc Delcroix +6
Target speech extraction is a technique to extract the target speaker's voice from mixture signals using a pre-recorded enrollment utterance that characterize the voice characteris…
Listen only to me! How well can target speech extraction handle false alarms?
Marc Delcroix, Keisuke Kinoshita, Tsubasa Ochiai +3
Target speech extraction (TSE) extracts the speech of a target speaker in a mixture given auxiliary clues characterizing the speaker, such as an enrollment utterance. TSE addresses…
Learning to Enhance or Not: Neural Network-Based Switching of Enhanced and Observed Signals for Overlapping Speech Recognition
Hiroshi Sato, Tsubasa Ochiai, Marc Delcroix +3
The combination of a deep neural network (DNN) -based speech enhancement (SE) front-end and an automatic speech recognition (ASR) back-end is a widely used approach to implement ov…
How Bad Are Artifacts?: Analyzing the Impact of Speech Enhancement Errors on ASR
Kazuma Iwamoto, Tsubasa Ochiai, Marc Delcroix +4
It is challenging to improve automatic speech recognition (ASR) performance in noisy conditions with single-channel speech enhancement (SE). In this paper, we investigate the cause…
Should We Always Separate?: Switching Between Enhanced and Observed Signals for Overlapping Speech Recognition
Hiroshi Sato, Tsubasa Ochiai, Marc Delcroix +3
Although recent advances in deep learning technology improved automatic speech recognition (ASR), it remains difficult to recognize speech when it overlaps other people's voices. S…