REVIEW 16 cited by
NISQA: A Deep CNN-Self-Attention Model for Multidimensional Speech Quality Prediction with Crowdsourced Datasets
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Signed reviews
read the original abstract
In this paper, we present an update to the NISQA speech quality prediction model that is focused on distortions that occur in communication networks. In contrast to the previous version, the model is trained end-to-end and the time-dependency modelling and time-pooling is achieved through a Self-Attention mechanism. Besides overall speech quality, the model also predicts the four speech quality dimensions Noisiness, Coloration, Discontinuity, and Loudness, and in this way gives more insight into the cause of a quality degradation. Furthermore, new datasets with over 13,000 speech files were created for training and validation of the model. The model was finally tested on a new, live-talking test dataset that contains recordings of real telephone calls. Overall, NISQA was trained and evaluated on 81 datasets from different sources and showed to provide reliable predictions also for unknown speech samples. The code, model weights, and datasets are open-sourced.
Forward citations
Cited by 16 Pith papers
-
Beyond Naturalness: Probing Automated Text-To-Speech Evaluators on Linguistically Grounded Dimensions
Automated TTS evaluators, both MOS predictors and Audio-LLM judges, systematically fail to detect most linguistically grounded speech errors, with MOS predictors collapsing onto signal-level artifacts.
-
CallScreenBench: Benchmarking On-Device Models as Phone Secretaries
A new phone-secretary benchmark shows quality scaling with capability, no triage scaling once degenerate baselines are subtracted, and more capable models relaying scam callback numbers more often.
-
AudioJudge: Understanding What Works in Large Audio Model Based Speech Evaluation
With prompt engineering (audio concatenation plus in-context examples), large audio models rank speech synthesis systems in line with human preferences, reaching up to 0.91 Spearman correlation.
-
LLM-Guided Reinforcement Learning for Audio-Visual Speech Enhancement
Using LLM-generated text descriptions of enhanced speech converted to sentiment scores as PPO rewards improves PESQ, STOI, and neural quality scores over supervised and DNSMOS-reward baselines on AVSEC-4.
-
Audio Jailbreak Attacks: Exposing Vulnerabilities in SpeechGPT in a White-Box Framework
By appending optimized token sequences to harmful speech, the authors achieve up to 89% attack success rate on SpeechGPT across six forbidden categories.
-
RoVo: Robust Voice Protection Against Unauthorized Speech Synthesis with Embedding-Level Perturbations
RoVo perturbs BARK codec embeddings instead of raw audio, and reports that speech-synthesis clones of protected voices are rejected by speaker verification 70+ percentage points more often, with better robustness to s...
-
Audio Large Language Models Can Be Descriptive Speech Quality Evaluators
Audio LLMs fine-tuned with token-level distillation against an LLM teacher can predict speech quality scores and generate natural-language descriptions, including A/B comparisons.
-
CS-ETS: Chaos-Inspired Samba-Based EMG-To-Speech Synthesis with Nonlinear Chaotic Losses
CS-ETS applies Lyapunov and detrended-fluctuation-analysis losses inside a Samba encoder, but its headline audio gains are confounded by a DTW alignment step not applied to baselines.
-
GenTSE: Enhancing Target Speaker Extraction via a Coarse-to-Fine Generative Language Model
A two-stage decoder-only language model with continuous embeddings and UTMOS-based preference fine-tuning reports improved target-speaker-extraction scores on Libri2Mix.
-
Schr\"odinger Bridge Mamba for One-Step Speech Enhancement
A Mamba-based speech enhancer trained with Schrödinger Bridge objectives produces strong denoising and dereverberation in one inference step with a low real-time factor.
-
A Survey of Automatic Evaluation Methods on Text, Visual and Speech Generations
A unified taxonomy and comparative meta-evaluation of automatic evaluation methods across text, vision, and speech generation, concluding that LLM-based evaluators dominate current practice.
-
Towards Flow-Matching-based TTS without Classifier-Free Guidance
Modifying the flow-matching training target lets F5-TTS synthesize speech without classifier-free guidance at inference, halving per-step cost and improving measured WER, SIM-O, and MOS.
-
Metis: A Foundation Speech Generation Model with Masked Generative Pre-training
A masked generative model pre-trained on unlabeled speech then fine-tuned per task matches or beats task-specific systems across TTS, voice conversion, speaker extraction, enhancement, and lip-to-speech.
-
Towards Improved Objective Perceptual Audio Quality Assessment -- Part 1: A Novel Data-Driven Cognitive Model
A cognitive weighting layer on top of PEAQ's distortion metrics improves prediction of unseen subjective audio quality scores across codec and source-separation databases.
-
Muyan-TTS: A Trainable Text-to-Speech Model Optimized for Podcast Scenarios with a $50K Budget
Muyan-TTS, a 3B-parameter LLM-based TTS model trained on 100,000+ hours of podcast audio, produces competitive zero-shot speech and runs at 0.33 seconds of inference per second of speech.
-
Overview of the Amphion Toolkit (v0.2)
Amphion v0.2 is an open-source toolkit for audio, music, and speech generation, adding a 101K-hour multilingual dataset, processing pipelines, and pretrained models.
Discussion (0). Continue with ORCID to comment.