Breaking the Quality--Intelligibility Trade-off in Streaming Target Speaker Extraction via Deep-Feature-Anchored Preference Optimization
Generative streaming models for Target Speaker Extraction (TSE) commonly exhibit a quality--intelligibility trade-off, wherein naive optimization for perceptual audio quality tends to degrade speech intelligibility, and conversely. We reveal that this trade-off arises not from the constraints of streaming architectures, but from an inappropriate choice of optimization anchor. Directly optimizing against audio quality metrics induces catastrophic reward hacking, where content critical to pronunciation and intelligibility is systematically erased to maximize a proxy score. To break this bottleneck, we propose two complementary improvements: an enlarged Conformer convolution kernel for richer local spectro-temporal modeling, and WavLM-anchored Direct Preference Optimization (DPO) fine-tuning strategy. DPO preference pairs are ranked by WavLM cosine similarity, a deep acoustic feature encoding both phonetic structure and speaker identity, providing an optimization anchor that resists hacking. Under a 560 ms streaming chunk size, the proposed method achieves a 10.9% relative intelligibility improvement (word error rate: 0.138 to 0.123), with marginal simultaneous gains in audio quality and speaker similarity.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Non-Monotonic Attention-based Read/Write Policy Learning for Simultaneous Translation
Simultaneous or streaming machine translation generates translation while reading the input stream. These systems face a quality/latency trade-off, aiming to achieve high translation quality similar to non-streaming mode…
Binary ClassificationMachine TranslationTranslationMirror Speculative Decoding: Breaking the Serial Barrier in LLM Inference
Speculative decoding accelerates LLM inference by using a draft model to look ahead, but gains are capped by the cost of autoregressive draft generation: increasing draft size elevates acceptance rates but introduces add…
Reconstruct! Don't Encode: Self-Supervised Representation Reconstruction Loss for High-Intelligibility and Low-Latency Streaming Neural Audio Codec
Neural audio codecs optimized for mel-spectrogram reconstruction often fail to preserve intelligibility. While semantic encoder distillation improves encoded representations, it does not guarantee content preservation in…
StarTSE: Towards Streaming Target Speaker Extraction via Chunk-wise Interleaved Splicing of Autoregressive Language Model
While generative models have set new benchmarks for Target Speaker Extraction (TSE), their inherent reliance on global context precludes deployment in real-time applications. Direct adaptation to streaming scenarios ofte…
Streaming T5-based Text-to-Speech Synthesis with Limited Lookahead
Streaming text-to-speech synthesis in cascaded LLM-TTS systems still faces latency challenges as most TTS models require full context before initiating generation. We present S5-TTS, a streaming variant of T5-TTS that en…
Text-To-Speech Synthesis