A DQN-style planner initialized from a pretrained LLM selects the system's emotion before response generation, using a hybrid reward of dataset imitation and GPT-4o-scored Plutchik theory, enabling streaming emotional TTS.
SpeechBERTScore: Reference-aware automatic evaluation of speech generation leveraging nlp evaluation metrics
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
abstract
While subjective assessments have been the gold standard for evaluating speech generation, there is a growing need for objective metrics that are highly correlated with human subjective judgments due to their cost efficiency. This paper proposes reference-aware automatic evaluation methods for speech generation inspired by evaluation metrics in natural language processing. The proposed SpeechBERTScore computes the BERTScore for self-supervised dense speech features of the generated and reference speech, which can have different sequential lengths. We also propose SpeechBLEU and SpeechTokenDistance, which are computed on speech discrete tokens. The evaluations on synthesized speech show that our method correlates better with human subjective ratings than mel cepstral distortion and a recent mean opinion score prediction model. Also, they are effective in noisy speech evaluation and have cross-lingual applicability.
representative citing papers
MOS-Bench benchmark shows that existing SSQA models struggle with out-of-domain generalization and that training on multiple diverse datasets improves robustness.
citing papers explorer
-
MOS-Bench: Benchmarking Generalization Abilities of Subjective Speech Quality Assessment Models
MOS-Bench benchmark shows that existing SSQA models struggle with out-of-domain generalization and that training on multiple diverse datasets improves robustness.