BLOOM-Net: Blockwise Optimization for Masking Networks Toward Scalable and Efficient Speech Enhancement
In this paper, we present a blockwise optimization method for masking-based networks (BLOOM-Net) for training scalable speech enhancement networks. Here, we design our network with a residual learning scheme and train the internal separator blocks sequentially to obtain a scalable masking-based deep neural network for speech enhancement. Its scalability lets it dynamically adjust the run-time complexity depending on the test time environment. To this end, we modularize our models in that they can flexibly accommodate varying needs for enhancement performance and constraints on the resources, incurring minimal memory or training overhead due to the added scalability. Our experiments on speech enhancement demonstrate that the proposed blockwise optimization method achieves the desired scalability with only a slight performance degradation compared to corresponding models trained end-to-end.
Code (2)
Tasks
Speech EnhancementSimilar Papers 제목 키워드 기반
On the Trainability of Masked Diffusion Language Models via Blockwise Locality
Masked diffusion language models (MDMs) have recently emerged as a promising alternative to standard autoregressive large language models (AR-LLMs), yet their optimization can be substantially less stable. We study block…
Blockwise SFT for Diffusion Language Models: Reconciling Bidirectional Attention and Autoregressive Decoding
Discrete diffusion language models have shown strong potential for text generation, yet standard supervised fine-tuning (SFT) misaligns with their semi-autoregressive inference: training randomly masks tokens across the …
Text GenerationM3PT: A Transformer for Multimodal, Multi-Party Social Signal Prediction with Person-aware Blockwise Attention
Understanding social signals in multi-party conversations is important for human-robot interaction and artificial social intelligence. Social signals include body pose, head pose, speech, and context-specific activities …
Incremental Blockwise Beam Search for Simultaneous Speech Translation with Controllable Quality-Latency Tradeoff
Blockwise self-attentional encoder models have recently emerged as one promising end-to-end approach to simultaneous speech translation. These models employ a blockwise beam search with hypothesis reliability scoring to …
TranslationDecoder-only Architecture for Streaming End-to-end Speech Recognition
Decoder-only language models (LMs) have been successfully adopted for speech-processing tasks including automatic speech recognition (ASR). The LMs have ample expressiveness and perform efficiently. This efficiency is a …
Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Decoderspeech-recognition+1