REVIEW 12 cited by
InstructTTSEval: Benchmarking Complex Natural-Language Instruction Following in Text-to-Speech Systems
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
InstructTTSEval: Benchmarking Complex Natural-Language Instruction Following in Text-to-Speech Systems
read the original abstract
In modern speech synthesis, paralinguistic information--such as a speaker's vocal timbre, emotional state, and dynamic prosody--plays a critical role in conveying nuance beyond mere semantics. Traditional Text-to-Speech (TTS) systems rely on fixed style labels or inserting a speech prompt to control these cues, which severely limits flexibility. Recent attempts seek to employ natural-language instructions to modulate paralinguistic features, substantially improving the generalization of instruction-driven TTS models. Although many TTS systems now support customized synthesis via textual description, their actual ability to interpret and execute complex instructions remains largely unexplored. In addition, there is still a shortage of high-quality benchmarks and automated evaluation metrics specifically designed for instruction-based TTS, which hinders accurate assessment and iterative optimization of these models. To address these limitations, we introduce InstructTTSEval, a benchmark for measuring the capability of complex natural-language style control. We introduce three tasks, namely Acoustic-Parameter Specification, Descriptive-Style Directive, and Role-Play, including English and Chinese subsets, each with 1k test cases (6k in total) paired with reference audio. We leverage Gemini as an automatic judge to assess their instruction-following abilities. Our evaluation of accessible instruction-following TTS systems highlights substantial room for further improvement. We anticipate that InstructTTSEval will drive progress toward more powerful, flexible, and accurate instruction-following TTS.
Forward citations
Cited by 12 Pith papers
-
ParaPairAudioBench: Paralinguistic Pairwise Audio Benchmark for LALM-as-a-Judge
ParaPairAudioBench is a new pairwise benchmark showing LALM judges lag human paralinguistic judgments by 32 percentage points with poor tie calibration across style, rate, emphasis, age, and gender.
-
MINT-Bench: A Comprehensive Multilingual Benchmark for Instruction-Following Text-to-Speech
MINT-Bench is a new benchmark using hierarchical taxonomy, multi-stage data pipeline, and hybrid evaluation to assess instruction-following TTS systems, revealing major gaps in compositional and paralinguistic controls.
-
NVBench: A Benchmark for Speech Synthesis with Non-Verbal Vocalizations
NVBench provides a standardized bilingual benchmark and evaluation protocol for assessing non-verbal vocalization generation, placement, and salience in text-to-speech systems.
-
CapTalk: Unified Voice Design for Single-Utterance and Dialogue Speech Generation
CapTalk unifies single-utterance and dialogue voice design via utterance- and speaker-level captions plus a hierarchical variational module for stable timbre with adaptive expression.
-
SwanTale: Unified Multi-Speaker Speech and Audio Generation for Instruct and Zero-Shot Tasks
SwanTale unifies instruction-driven and zero-shot speech and audio generation in one 48 kHz model, with a large captioning pipeline, and reports leading scores on several expressiveness and instruction-following benchmarks.
-
Beyond Prompt Adherence: Auditing Attribute-Level Voice Control in Speech Generation
A paired audit of three TTS systems shows that descriptor-aligned voice changes come with off-target acoustic shifts, and a candidate selector reduces these shifts at inference time.
-
RW-Voice-EQ Bench: A Real World Benchmark for Evaluating Voice AI Systems
No voice AI system dominates all capabilities; naturalness, expressiveness, identity stability, audio sensitivity, and transcription robustness vary independently, so voice AI should be evaluated as a multidimensional...
-
Auditing Protocol-Level Shortcuts in Large Audio Language Model Judges for Speech Evaluation
Several LALM judges copy wrong specialist labels or lock onto presentation order instead of listening to audio, so aggregate human agreement overstates judge validity.
-
Improving Text-to-Audio Instruction Following via Fine-Grained Feedback from Audio-Aware Large Language Models
Using audio-aware LLMs to judge event presence and temporal order as DPO rewards improves multi-event text-to-audio instruction following.
-
Is Natural Always Appropriate? Investigating Naturalness and Appropriateness Across Different Domains for TTS Evaluation
Appropriateness of TTS varies independently across domains while naturalness scores penalize stylized speech and reward spontaneity.
-
Qwen3-TTS Technical Report
Qwen3-TTS delivers state-of-the-art multilingual TTS performance with 3-second voice cloning, description control, and ultra-low-latency streaming via dual tokenizers and a dual-track LM architecture trained on over 5...
-
AgentSteerTTS: A Multi-Agent Closed-Loop Framework for Composite-Instruction Text-to-Speech
AgentSteerTTS proposes a multi-agent framework with adversarial disentanglement, dual-stream anchoring via acoustic prototypes, and fast-slow feedback to achieve intent-faithful expressive TTS for composite instructions.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.