Effects of Layer Freezing on Transferring a Speech Recognition System to Under-resourced Languages
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.
Code (1)
Tasks
Automatic Speech RecognitionAutomatic Speech Recognition (ASR)speech-recognitionSpeech RecognitionSimilar Papers 제목 키워드 기반
Quantifying and Maximizing the Benefits of Back-End Noise Adaption on Attention-Based Speech Recognition Models
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 RecognitionA Sidecar Separator Can Convert a Single-Talker Speech Recognition System to a Multi-Talker One
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 RecognitionOptimizing Multi-Stuttered Speech Classification: Leveraging Whisper's Encoder for Efficient Parameter Reduction in Automated Assessment
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 RecognitionMultiple Representation Transfer from Large Language Models to End-to-End ASR Systems
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 RecognitionOn-Device Speaker Anonymization of Acoustic Embeddings for ASR based onFlexible Location Gradient Reversal Layer
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