Search Results for author:
Found 26 papers, 1 papers with code
Microphone Array Geometry Independent Multi-Talker Distant ASR: NTT System for the DASR Task of the CHiME-8 Challenge
Our system performs speaker counting, diarization, and ASR.
Guided Speaker Embedding
This paper proposes a guided speaker embedding extraction system, which extracts speaker embeddings of the target speaker using speech activities of target and interference speakers as clues.
Investigation of Speaker Representation for Target-Speaker Speech Processing
To this end, for the TS-ASR, TSE, and p-VAD tasks, we compare pre-trained speaker encoders (i. e., self-supervised or speaker recognition models) that compute speaker embeddings from pre-recorded enrollment speech of the target speaker with ideal speaker embeddings derived directly from the target speaker's identity in the form of a one-hot vector.
Alignment-Free Training for Transducer-based Multi-Talker ASR
Thus, MT-RNNT-AFT can be trained without relying on accurate alignments, and it can recognize all speakers' speech with just one round of encoder processing.
Boosting Hybrid Autoregressive Transducer-based ASR with Internal Acoustic Model Training and Dual Blank Thresholding
A hybrid autoregressive transducer (HAT) is a variant of neural transducer that models blank and non-blank posterior distributions separately.
NTT Multi-Speaker ASR System for the DASR Task of CHiME-8 Challenge
We present a distant automatic speech recognition (DASR) system developed for the CHiME-8 DASR track.
Recursive Attentive Pooling for Extracting Speaker Embeddings from Multi-Speaker Recordings
This paper proposes a method for extracting speaker embedding for each speaker from a variable-length recording containing multiple speakers.
Sentence-wise Speech Summarization: Task, Datasets, and End-to-End Modeling with LM Knowledge Distillation
Using these datasets, our study evaluates two types of Transformer-based models: 1) cascade models that combine ASR and strong text summarization models, and 2) end-to-end (E2E) models that directly convert speech into a text summary.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+4
SpeakerBeam-SS: Real-time Target Speaker Extraction with Lightweight Conv-TasNet and State Space Modeling
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.
Lightweight Zero-shot Text-to-Speech with Mixture of Adapters
These modules enhance the ability to adapt a wide variety of speakers in a zero-shot manner by selecting appropriate adapters associated with speaker characteristics on the basis of speaker embeddings.
Applying LLMs for Rescoring N-best ASR Hypotheses of Casual Conversations: Effects of Domain Adaptation and Context Carry-over
We investigate the effects of domain adaptation of the LLM and context carry-over when performing N-best rescoring.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Probing Self-supervised Learning Models with Target Speech Extraction
TSE uniquely requires both speaker identification and speech separation, distinguishing it from other tasks in the Speech processing Universal PERformance Benchmark (SUPERB) evaluation.
What Do Self-Supervised Speech and Speaker Models Learn? New Findings From a Cross Model Layer-Wise Analysis
Our analysis unveils that 1) the capacity to represent content information is somewhat unrelated to enhanced speaker representation, 2) specific layers of speech SSL models would be partly specialized in capturing linguistic information, and 3) speaker SSL models tend to disregard linguistic information but exhibit more sophisticated speaker representation.
Noise-robust zero-shot text-to-speech synthesis conditioned on self-supervised speech-representation model with adapters
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 speaker characteristics very accurately.
SpeechGLUE: How Well Can Self-Supervised Speech Models Capture Linguistic Knowledge?
Self-supervised learning (SSL) for speech representation has been successfully applied in various downstream tasks, such as speech and speaker recognition.
Transfer Learning from Pre-trained Language Models Improves End-to-End Speech Summarization
End-to-end speech summarization (E2E SSum) directly summarizes input speech into easy-to-read short sentences with a single model.
Improving Scheduled Sampling for Neural Transducer-based ASR
Experiments in three datasets confirm that RNNT trained with our SS approach achieves the best ASR performance.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
Knowledge Distillation for Neural Transducer-based Target-Speaker ASR: Exploiting Parallel Mixture/Single-Talker Speech Data
Neural transducer (RNNT)-based target-speaker speech recognition (TS-RNNT) directly transcribes a target speaker's voice from a multi-talker mixture.
Downstream Task Agnostic Speech Enhancement with Self-Supervised Representation Loss
In this work, we propose a new SE training criterion that minimizes the distance between clean and enhanced signals in the feature representation of the SSL model to alleviate the mismatch.
Exploration of Language Dependency for Japanese Self-Supervised Speech Representation Models
However, since the two settings have been studied individually in general, there has been little research focusing on how effective a cross-lingual model is in comparison with a monolingual model.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Zero-shot text-to-speech synthesis conditioned using self-supervised speech representation model
This paper proposes a zero-shot text-to-speech (TTS) conditioned by a self-supervised speech-representation model acquired through self-supervised learning (SSL).
Leveraging Large Text Corpora for End-to-End Speech Summarization
The first technique is to utilize a text-to-speech (TTS) system to generate synthesized speech, which is used for E2E SSum training with the text summary.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
On the Use of Modality-Specific Large-Scale Pre-Trained Encoders for Multimodal Sentiment Analysis
This paper investigates the effectiveness and implementation of modality-specific large-scale pre-trained encoders for multimodal sentiment analysis~(MSA).
Deep versus Wide: An Analysis of Student Architectures for Task-Agnostic Knowledge Distillation of Self-Supervised Speech Models
We investigate the performance on SUPERB while varying the structure and KD methods so as to keep the number of parameters constant; this allows us to analyze the contribution of the representation introduced by varying the model architecture.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+4
Cross-Modal Transformer-Based Neural Correction Models for Automatic Speech Recognition
However, the conventional method cannot take into account the relationships between these two different modal inputs because the input contexts are separately encoded for each modal.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
End-to-End Automatic Speech Recognition with Deep Mutual Learning
We also show that combining DML with the existing training techniques effectively improves ASR performance.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
