Differentiable Reward Optimization for LLM based TTS system

• URL: http://arxiv.org/abs/2507.05911v1
• Date: Tue, 08 Jul 2025 11:57:16 GMT
• Title: Differentiable Reward Optimization for LLM based TTS system
• Authors: Changfeng Gao, Zhihao Du, Shiliang Zhang,
• Abstract summary: This paper proposes a novel Differentiable Reward Optimization (DiffRO) method aimed at enhancing the performance of neural language models based text-to-speech (TTS) systems.<n>In contrast to conventional reinforcement learning from human feedback (RLHF), DiffRO directly computes the rewards based on neural tokens, rather than relying on synthesized audio.<n>We introduce a multi-task reward (MTR) model which can provide feedback from different perspectives and find that it can augment the system's capability to follow instructions effectively.
• Score: 46.658935067247945
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: This paper proposes a novel Differentiable Reward Optimization (DiffRO) method aimed at enhancing the performance of neural codec language models based text-to-speech (TTS) systems. In contrast to conventional reinforcement learning from human feedback (RLHF) approaches applied to TTS, DiffRO directly compute the rewards based on neural codec tokens, rather than relying on synthesized audio. Furthermore, we employ the Gumbel-Softmax technique to render the reward function differentiable, thereby streamlining the RLHF training process. Additionally, we introduce a multi-task reward (MTR) model which can provide feedback from different perspectives and find that it can augment the system's capability to follow instructions effectively.Experimental results indicate that DiffRO significantly improves the pronunciation accuracy of the TTS system, achieving state-of-the-art (SOTA) WER results on the seed-tts-eval benchmark. Moreover, with the integration of the MTR model, we demonstrate the ability to control emotional and quality attributes in a zero-shot manner.

Related papers

• Codec-ASR: Training Performant Automatic Speech Recognition Systems with Discrete Speech Representations [16.577870835480585]
  We present a comprehensive analysis on building ASR systems with discrete codes. We investigate different methods for training such as quantization schemes and time-domain vs spectral feature encodings. We introduce a pipeline that outperforms Encodec at similar bit-rate.
  arXiv  Detail & Related papers  (2024-07-03T20:51:41Z)
• Robust Zero-Shot Text-to-Speech Synthesis with Reverse Inference Optimization [34.51491788470738]
  We propose reverse inference optimization (RIO) to enhance the robustness of autoregressive-model-based text-to-speech (TTS) systems. RIO uses reverse inference as the standard to select exemplars used in RLHF from the speech samples generated by the TTS system itself. RIO significantly improves the stability of zero-shot TTS performance by reducing the discrepancies between training and inference conditions.
  arXiv  Detail & Related papers  (2024-07-02T13:04:04Z)
• Improved Contextual Recognition In Automatic Speech Recognition Systems By Semantic Lattice Rescoring [4.819085609772069]
  We propose a novel approach for enhancing contextual recognition within ASR systems via semantic lattice processing. Our solution consists of using Hidden Markov Models and Gaussian Mixture Models (HMM-GMM) along with Deep Neural Networks (DNN) models for better accuracy. We demonstrate the effectiveness of our proposed framework on the LibriSpeech dataset with empirical analyses.
  arXiv  Detail & Related papers  (2023-10-14T23:16:05Z)
• Improving Audio-Visual Speech Recognition by Lip-Subword Correlation Based Visual Pre-training and Cross-Modal Fusion Encoder [58.523884148942166]
  We propose two novel techniques to improve audio-visual speech recognition (AVSR) under a pre-training and fine-tuning training framework. First, we explore the correlation between lip shapes and syllable-level subword units in Mandarin to establish good frame-level syllable boundaries from lip shapes. Next, we propose an audio-guided cross-modal fusion encoder (CMFE) neural network to utilize main training parameters for multiple cross-modal attention layers.
  arXiv  Detail & Related papers  (2023-08-14T08:19:24Z)
• Contextual-Utterance Training for Automatic Speech Recognition [65.4571135368178]
  We propose a contextual-utterance training technique which makes use of the previous and future contextual utterances. Also, we propose a dual-mode contextual-utterance training technique for streaming automatic speech recognition (ASR) systems. The proposed technique is able to reduce both the WER and the average last token emission latency by more than 6% and 40ms relative.
  arXiv  Detail & Related papers  (2022-10-27T08:10:44Z)
• Adaptive re-calibration of channel-wise features for Adversarial Audio Classification [0.0]
  We propose a recalibration of features using attention feature fusion for synthetic speech detection. We compare its performance against different detection methods including End2End models and Resnet-based models. We also demonstrate that the combination of Linear frequency cepstral coefficients (LFCC) and Mel Frequency cepstral coefficients (MFCC) using the attentional feature fusion technique creates better input features representations.
  arXiv  Detail & Related papers  (2022-10-21T04:21:56Z)
• Neural Model Reprogramming with Similarity Based Mapping for Low-Resource Spoken Command Recognition [71.96870151495536]
  We propose a novel adversarial reprogramming (AR) approach for low-resource spoken command recognition (SCR) The AR procedure aims to modify the acoustic signals (from the target domain) to repurpose a pretrained SCR model. We evaluate the proposed AR-SCR system on three low-resource SCR datasets, including Arabic, Lithuanian, and dysarthric Mandarin speech.
  arXiv  Detail & Related papers  (2021-10-08T05:07:35Z)
• Automated Audio Captioning using Transfer Learning and Reconstruction Latent Space Similarity Regularization [21.216783537997426]
  We propose an architecture that is able to better leverage the acoustic features provided by PANNs for the Automated Audio Captioning Task. We also introduce a novel self-supervised objective, Reconstruction Latent Space Similarity Regularization (RLSSR)
  arXiv  Detail & Related papers  (2021-08-10T13:49:41Z)
• Pretraining Techniques for Sequence-to-Sequence Voice Conversion [57.65753150356411]
  Sequence-to-sequence (seq2seq) voice conversion (VC) models are attractive owing to their ability to convert prosody. We propose to transfer knowledge from other speech processing tasks where large-scale corpora are easily available, typically text-to-speech (TTS) and automatic speech recognition (ASR) We argue that VC models with such pretrained ASR or TTS model parameters can generate effective hidden representations for high-fidelity, highly intelligible converted speech.
  arXiv  Detail & Related papers  (2020-08-07T11:02:07Z)
• Learning to Learn Kernels with Variational Random Features [118.09565227041844]
  We introduce kernels with random Fourier features in the meta-learning framework to leverage their strong few-shot learning ability. We formulate the optimization of MetaVRF as a variational inference problem. We show that MetaVRF delivers much better, or at least competitive, performance compared to existing meta-learning alternatives.
  arXiv  Detail & Related papers  (2020-06-11T18:05:29Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.