Search Results for author:
Found 15 papers, 1 papers with code
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).
Multimodal Attention Fusion for Target Speaker Extraction
Recently an audio-visual target speaker extraction has been proposed that extracts target speech by using complementary audio and visual clues.
Should We Always Separate?: Switching Between Enhanced and Observed Signals for Overlapping Speech Recognition
', we analyze ASR performance on observed and enhanced speech at various noise and interference conditions, and show that speech enhancement degrades ASR under some conditions even for overlapping speech.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
Learning to Enhance or Not: Neural Network-Based Switching of Enhanced and Observed Signals for Overlapping Speech Recognition
To mitigate the degradation, we introduced a rule-based method to switch the ASR input between the enhanced and observed signals, which showed promising results.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
How Bad Are Artifacts?: Analyzing the Impact of Speech Enhancement Errors on ASR
The artifact component is defined as the SE error signal that cannot be represented as a linear combination of speech and noise sources.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Listen only to me! How well can target speech extraction handle false alarms?
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.
Strategies to Improve Robustness of Target Speech Extraction to Enrollment Variations
Experimental validation reveals the effectiveness of both worst-enrollment target training and SI-loss training to improve robustness against enrollment variations, by increasing speaker discriminability.
Streaming Target-Speaker ASR with Neural Transducer
We confirm in experiments that our TS-ASR achieves comparable recognition performance with conventional cascade systems in the offline setting, while reducing computation costs and realizing streaming TS-ASR.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Multi-Perspective Document Revision
To model the task, we design a novel Japanese multi-perspective document revision dataset that simultaneously handles seven perspectives to improve the readability and clarity of a document.
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.
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.
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)
+2
End-to-End Joint Target and Non-Target Speakers ASR
Target-speaker ASR systems are a promising way to only transcribe a target speaker's speech by enrolling the target speaker's information.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
How does end-to-end speech recognition training impact speech enhancement artifacts?
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 distortion} generated by single-channel SE on ASR.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
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.
