mlsanityData to 7 Oct 2026

SpeechBERTScore: Reference-Aware Automatic Evaluation of Speech Generation Leveraging NLP Evaluation Metrics

arXiv 2401.16812 ↗First posted 30 Jan 2024cs.SD eess.AScited by 38

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 38 papers in the map (data through 7 Oct 2026). First posted on arXiv 30 Jan 2024.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 2; 2025: 20; 2026: 16.

38 papers.

Sort:

By area:

  1. 2024Preference Tuning with Human Feedback on Language, Speech, and Vision Tasks: A Surveycited by 23
  2. 2025AnyEnhance: A Unified Generative Model with Prompt-Guidance and Self-Critic for Voice Enhancementcited by 23
  3. 2025LLaSE-G1: Incentivizing Generalization Capability for LLaMA-based Speech Enhancementcited by 19
  4. 2024Enabling Auditory Large Language Models for Automatic Speech Quality Evaluationcited by 13
  5. 2025Universal Speech Enhancement with Regression and Generative Mambacited by 7
  6. 2025Multi-Metric Preference Alignment for Generative Speech Restorationcited by 7
  7. 2025LauraTSE: Target Speaker Extraction using Auto-Regressive Decoder-Only Language Modelscited by 5
  8. 2025PASE: Leveraging the Phonological Prior of WavLM for Low-Hallucination Generative Speech Enhancementcited by 5
  9. 2026FlowSE-GRPO: Training Flow Matching Speech Enhancement via Online Reinforcement Learningcited by 5
  10. 2025Articulatory Feature Prediction from Surface EMG during Speech Productioncited by 4
  11. 2025Voice of a Continent: Mapping Africa's Speech Technology Frontiercited by 4
  12. 2025Real-Time Streamable Generative Speech Restoration with Flow Matchingcited by 4
26 more
  1. 2025SenSE: Semantic-Aware High-Fidelity Universal Speech Enhancementcited by 3
  2. 2025TS-URGENet: A Three-stage Universal Robust and Generalizable Speech Enhancement Networkcited by 2
  3. 2025High-Fidelity Speech Enhancement via Discrete Audio Tokenscited by 2
  4. 2025Schr"odinger Bridge Mamba for One-Step Speech Enhancementcited by 2
  5. 2026TTS-PRISM: A Perceptual Reasoning and Interpretable Speech Model for Fine-Grained Diagnosiscited by 2
  6. 2025Incorporating Linguistic Constraints from External Knowledge Source for Audio-Visual Target Speech Extractioncited by 1
  7. 2025GenTSE: Enhancing Target Speaker Extraction via a Coarse-to-Fine Generative Language Modelcited by 1
  8. 2026Do Neural Codecs Generalize? A Controlled Study Across Unseen Languages and Non-Speech Taskscited by 1
  9. 2026Geneses: Unified Generative Speech Enhancement and Separationcited by 1
  10. 2026Residual Tokens Enhance Masked Autoencoders for Speech Modelingcited by 1
  11. 2026StarTSE: Towards Streaming Target Speaker Extraction via Chunk-wise Interleaved Splicing of Autoregressive Language Modelcited by 1
  12. 2025BnTTS: Few-Shot Speaker Adaptation in Low-Resource Settingcited by 0
  13. 2025Score-Based Training for Energy-Based TTS Modelscited by 0
  14. 2025SpeechOp: Inference-Time Task Composition for Generative Speech Processingcited by 0
  15. 2025Assessing speech quality metrics for evaluation of neural audio codecs under clean speech conditionscited by 0
  16. 2025ELEGANCE: Efficient LLM Guidance for Audio-Visual Target Speech Extractioncited by 0
  17. 2026SLM-SS: Speech Language Model for Generative Speech Separationcited by 0
  18. 2026SLD-L2S: Hierarchical Subspace Latent Diffusion for High-Fidelity Lip to Speech Synthesiscited by 0
  19. 2026Absorbing Discrete Diffusion for Speech Enhancementcited by 0
  20. 2026More Data, Fewer Diacritics: Scaling Arabic TTScited by 0
  21. 2026StuPASE: Towards Low-Hallucination Studio-Quality Generative Speech Enhancementcited by 0
  22. 2026LLM-Guided Reinforcement Learning for Audio-Visual Speech Enhancementcited by 0
  23. 2026UniPASE: A Generative Model for Universal Speech Enhancement with High Fidelity and Low Hallucinationscited by 0
  24. 2026Self-EmoQ: Plutchik-Guided Value-based Planning to Drive Streaming Emotional TTScited by 0
  25. 2026PhASE-Flow: Phonetic-Conditioned Acoustic Flow Matching in SSL Representation Domain for Speech Enhancementcited by 0
  26. 2026Quieter Than the Room: Representation Drift and Task Robustness in Speech Encoderscited by 0