paper-with-me

Papers

Effects of Layer Freezing on Transferring a Speech Recognition System to Under-resourced Languages

2021-02-08 · KONVENS (WS) 2021 9 · Onno Eberhard, Torsten Zesch

In this paper, we investigate the effect of layer freezing on the effectiveness of model transfer in the area of automatic speech recognition. We experiment with Mozilla's DeepSpeech architecture on German and Swiss German speech datasets and compare the results of either training from scratch vs. transferring a pre-trained model. We compare different layer freezing schemes and find that even freezing only one layer already significantly improves results.

📄 PDF Abstract BibTeX arXiv:2102.04097

Code (1)

onnoeberhard/deepspeech 공식 구현 tf

Tasks

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)speech-recognitionSpeech Recognition

Similar Papers 제목 키워드 기반

Quantifying and Maximizing the Benefits of Back-End Noise Adaption on Attention-Based Speech Recognition Models

2021-05-03 · Coleman Hooper, Thierry Tambe, Gu-Yeon Wei

This work analyzes how attention-based Bidirectional Long Short-Term Memory (BLSTM) models adapt to noise-augmented speech. We identify crucial components for noise adaptation in BLSTM models by freezing model components…

speech-recognitionSpeech Recognition

A Sidecar Separator Can Convert a Single-Talker Speech Recognition System to a Multi-Talker One

2023-02-20 · Lingwei Meng, Jiawen Kang, Mingyu Cui, Yuejiao Wang 외

Although automatic speech recognition (ASR) can perform well in common non-overlapping environments, sustaining performance in multi-talker overlapping speech recognition remains challenging. Recent research revealed tha…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)speech-recognitionSpeech Recognition

Optimizing Multi-Stuttered Speech Classification: Leveraging Whisper's Encoder for Efficient Parameter Reduction in Automated Assessment

2024-06-09 · Huma Ameer, Seemab Latif, Mehwish Fatima

The automated classification of stuttered speech has significant implications for timely assessments providing assistance to speech language pathologists. Despite notable advancements in the field, the cases in which mul…

Multi-Label ClassificationMUlTI-LABEL-ClASSIFICATIONspeech-recognitionSpeech Recognition

Multiple Representation Transfer from Large Language Models to End-to-End ASR Systems

2023-09-07 · Takuma Udagawa, Masayuki Suzuki, Gakuto Kurata, Masayasu Muraoka 외

Transferring the knowledge of large language models (LLMs) is a promising technique to incorporate linguistic knowledge into end-to-end automatic speech recognition (ASR) systems. However, existing works only transfer a …

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)speech-recognitionSpeech Recognition

On-Device Speaker Anonymization of Acoustic Embeddings for ASR based onFlexible Location Gradient Reversal Layer

2023-07-25 · Md Asif Jalal, Pablo Peso Parada, Jisi Zhang, Karthikeyan Saravanan 외

Smart devices serviced by large-scale AI models necessitates user data transfer to the cloud for inference. For speech applications, this means transferring private user information, e.g., speaker identity. Our paper pro…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Speaker anonymizationSpeaker Recognition+2