Rethinking MUSHRA: Addressing Modern Challenges in Text-to-Speech Evaluation

• URL: http://arxiv.org/abs/2411.12719v1
• Date: Tue, 19 Nov 2024 18:37:45 GMT
• Title: Rethinking MUSHRA: Addressing Modern Challenges in Text-to-Speech Evaluation
• Authors: Praveen Srinivasa Varadhan, Amogh Gulati, Ashwin Sankar, Srija Anand, Anirudh Gupta, Anirudh Mukherjee, Shiva Kumar Marepally, Ankur Bhatia, Saloni Jaju, Suvrat Bhooshan, Mitesh M. Khapra,
• Abstract summary: MUSHRA test is a promising alternative for evaluating TTS systems simultaneously. We show that its reliance on matching human reference speech unduly penalises the scores of modern TTS systems. We propose two refined variants of the MUSHRA test.
• Score: 12.954531089716008
• License:
• Abstract: Despite rapid advancements in TTS models, a consistent and robust human evaluation framework is still lacking. For example, MOS tests fail to differentiate between similar models, and CMOS's pairwise comparisons are time-intensive. The MUSHRA test is a promising alternative for evaluating multiple TTS systems simultaneously, but in this work we show that its reliance on matching human reference speech unduly penalises the scores of modern TTS systems that can exceed human speech quality. More specifically, we conduct a comprehensive assessment of the MUSHRA test, focusing on its sensitivity to factors such as rater variability, listener fatigue, and reference bias. Based on our extensive evaluation involving 471 human listeners across Hindi and Tamil we identify two primary shortcomings: (i) reference-matching bias, where raters are unduly influenced by the human reference, and (ii) judgement ambiguity, arising from a lack of clear fine-grained guidelines. To address these issues, we propose two refined variants of the MUSHRA test. The first variant enables fairer ratings for synthesized samples that surpass human reference quality. The second variant reduces ambiguity, as indicated by the relatively lower variance across raters. By combining these approaches, we achieve both more reliable and more fine-grained assessments. We also release MANGO, a massive dataset of 47,100 human ratings, the first-of-its-kind collection for Indian languages, aiding in analyzing human preferences and developing automatic metrics for evaluating TTS systems.

Related papers

• Beyond Oversmoothing: Evaluating DDPM and MSE for Scalable Speech Synthesis in ASR [13.307889110301502]
  We compare Denoising Diffusion Probabilistic Models (DDPM) to Mean Squared Error (MSE) based models for TTS, when used for ASR model training. We find that for a given model size, DDPM can make better use of more data, and a more diverse set of speakers, than MSE models. We achieve the best reported ratio between real and synthetic speech WER to date (1.46), but also find that a large gap remains.
  arXiv  Detail & Related papers  (2024-10-16T06:35:56Z)
• Beyond correlation: The impact of human uncertainty in measuring the effectiveness of automatic evaluation and LLM-as-a-judge [51.93909886542317]
  We show how a single aggregate correlation score can obscure differences between human behavior and automatic evaluation methods. We propose stratifying results by human label uncertainty to provide a more robust analysis of automatic evaluation performance.
  arXiv  Detail & Related papers  (2024-10-03T03:08:29Z)
• Enhancing Zero-shot Text-to-Speech Synthesis with Human Feedback [39.54647336161013]
  We propose a sampling-annotating-learning framework tailored to text-to-speech (TTS) optimization. We show that UNO considerably improves the zero-shot performance of TTS models in terms of MOS, word error rate, and speaker similarity. We also present a remarkable ability of UNO that it can adapt to the desired speaking style in emotional TTS seamlessly and flexibly.
  arXiv  Detail & Related papers  (2024-06-02T07:54:33Z)
• Revisiting the Gold Standard: Grounding Summarization Evaluation with Robust Human Evaluation [136.16507050034755]
  Existing human evaluation studies for summarization either exhibit a low inter-annotator agreement or have insufficient scale. We propose a modified summarization salience protocol, Atomic Content Units (ACUs), which is based on fine-grained semantic units. We curate the Robust Summarization Evaluation (RoSE) benchmark, a large human evaluation dataset consisting of 22,000 summary-level annotations over 28 top-performing systems.
  arXiv  Detail & Related papers  (2022-12-15T17:26:05Z)
• Predicting pairwise preferences between TTS audio stimuli using parallel ratings data and anti-symmetric twin neural networks [24.331098975217596]
  We propose a model based on anti-symmetric twin neural networks, trained on pairs of waveforms and their corresponding preference scores. To obtain a large training set we convert listeners' ratings from MUSHRA tests to values that reflect how often one stimulus in the pair was rated higher than the other. Our results compare favourably to a state-of-the-art model trained to predict MOS scores.
  arXiv  Detail & Related papers  (2022-09-22T13:34:22Z)
• Is Automated Topic Model Evaluation Broken?: The Incoherence of Coherence [62.826466543958624]
  We look at the standardization gap and the validation gap in topic model evaluation. Recent models relying on neural components surpass classical topic models according to these metrics. We use automatic coherence along with the two most widely accepted human judgment tasks, namely, topic rating and word intrusion.
  arXiv  Detail & Related papers  (2021-07-05T17:58:52Z)
• SMURF: SeMantic and linguistic UndeRstanding Fusion for Caption Evaluation via Typicality Analysis [20.026835809227283]
  We introduce "typicality", a new formulation of evaluation rooted in information theory. We show how these decomposed dimensions of semantics and fluency provide greater system-level insight into captioner differences. Our proposed metrics along with their combination, SMURF, achieve state-of-the-art correlation with human judgment when compared with other rule-based evaluation metrics.
  arXiv  Detail & Related papers  (2021-06-02T19:58:20Z)
• Towards Quantifiable Dialogue Coherence Evaluation [126.55560816209756]
  Quantifiable Dialogue Coherence Evaluation (QuantiDCE) is a novel framework aiming to train a quantifiable dialogue coherence metric. QuantiDCE includes two training stages, Multi-Level Ranking (MLR) pre-training and Knowledge Distillation (KD) fine-tuning. Experimental results show that the model trained by QuantiDCE presents stronger correlations with human judgements than the other state-of-the-art metrics.
  arXiv  Detail & Related papers  (2021-06-01T14:11:17Z)
• Towards Automatic Evaluation of Dialog Systems: A Model-Free Off-Policy Evaluation Approach [84.02388020258141]
  We propose a new framework named ENIGMA for estimating human evaluation scores based on off-policy evaluation in reinforcement learning. ENIGMA only requires a handful of pre-collected experience data, and therefore does not involve human interaction with the target policy during the evaluation. Our experiments show that ENIGMA significantly outperforms existing methods in terms of correlation with human evaluation scores.
  arXiv  Detail & Related papers  (2021-02-20T03:29:20Z)
• Evaluation Toolkit For Robustness Testing Of Automatic Essay Scoring Systems [64.4896118325552]
  We evaluate the current state-of-the-art AES models using a model adversarial evaluation scheme and associated metrics. We find that AES models are highly overstable. Even heavy modifications(as much as 25%) with content unrelated to the topic of the questions do not decrease the score produced by the models.
  arXiv  Detail & Related papers  (2020-07-14T03:49:43Z)

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.