REVIEW 14 cited by
Emilia: An Extensive, Multilingual, and Diverse Speech Dataset for Large-Scale Speech Generation
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
read the original abstract
Recent advancements in speech generation models have been significantly driven by the use of large-scale training data. However, producing highly spontaneous, human-like speech remains a challenge due to the scarcity of large, diverse, and spontaneous speech datasets. In response, we introduce Emilia, the first large-scale, multilingual, and diverse speech generation dataset. Emilia starts with over 101k hours of speech across six languages, covering a wide range of speaking styles to enable more natural and spontaneous speech generation. To facilitate the scale-up of Emilia, we also present Emilia-Pipe, the first open-source preprocessing pipeline designed to efficiently transform raw, in-the-wild speech data into high-quality training data with speech annotations. Experimental results demonstrate the effectiveness of both Emilia and Emilia-Pipe. Demos are available at: https://emilia-dataset.github.io/Emilia-Demo-Page/.
Forward citations
Cited by 14 Pith papers
-
Investigating Codec-Internal Latent Audio Watermarking for Neural Codec Robustness
Embedding watermarks inside a codec-like autoencoder's continuous latent space improves EnCodec-24k bit accuracy to ~95–97%, but the gain is in-distribution and does not transfer to EnCodec-16k.
-
StellarTTS: Sparse Temporal Embedding for Low-Latency and Robust Speech Synthesis
A mobile-oriented 83M-parameter masked transformer with sparse phone-anchored temporal embeddings achieves RTF 0.08 and lower WER than MaskGCT/F5-TTS on Seed-TTS test sets.
-
DLLM-TTS: Block Discrete Diffusion Language Model for Text-to-Speech Synthesis
Block discrete diffusion over X-Codec2 tokens yields competitive zero-shot TTS with 0.6B parameters, 20K training hours, and a 0.15 real-time factor.
-
Making Separation-First Multi-Stream Audio Watermarking Feasible via Joint Training
Jointly training the watermark embedder/detector with the source separator enables ~1% bit-error-rate recovery of per-stem watermarks after mixing and separation, where independent training yields 15–35%.
-
UniVoice: Unifying Autoregressive ASR and Flow-Matching based TTS with Large Language Models
A single LLM can do ASR and zero-shot TTS on continuous speech features by switching between causal and bidirectional attention, reaching competitive but not state-of-the-art results.
-
Over-the-Air Adversarial Attack Detection: from Datasets to Defenses
AdvSV 2.0 provides 629k adversarial and bona fide audio samples for automatic speaker verification, with a neural replay simulator attack and a one-class contrastive domain-aligned detector reaching 11.2% EER.
-
AudioCodecBench: A Comprehensive Benchmark for Audio Codec Evaluation
A four-part benchmark plus a semantic/acoustic token taxonomy for comparing audio codecs, with correlation analysis across ten models.
-
Whilter: A Whisper-based Data Filter for "In-the-Wild" Speech Corpora Using Utterance-level Multi-Task Classification
A multitask classifier built on Whisper features flags multi-speaker, non-English, music, noisy, and synthetic speech clips in large in-the-wild corpora, and a new 21k-clip labeled dataset is released.
-
NonverbalTTS: A Public English Corpus of Text-Aligned Nonverbal Vocalizations with Emotion Annotations for Text-to-Speech
The authors release NonverbalTTS, a 17-hour open dataset with nonverbal vocalization and emotion annotations, and show that fine-tuning an open TTS model on it yields performance comparable to CosyVoice2.
-
Ming-Omni: A Unified Multimodal Model for Perception and Generation
A single model with modality-specific routing processes image, text, audio, and video inputs and generates text, speech, and images, with public benchmarks reported across all of these abilities.
-
REF-VC: Robust, Expressive and Fast Zero-Shot Voice Conversion with Diffusion Transformers
REF-VC is a zero-shot voice conversion system that random-erases redundant parts of speech-embedding features to stay robust to noise, and uses shortcut-distilled flow matching to convert speech in only four steps.
-
StreamFlow: Streaming Flow Matching with Block-wise Guided Attention Mask for Speech Token Decoding
StreamFlow achieves streaming speech token decoding with 180 ms first-packet latency by using hierarchical block-wise attention masks in a DiT flow matching model.
-
From Tens of Hours to Tens of Thousands: Scaling Back-Translation for Speech Recognition
Fine-tuning TTS models on tens of hours of real audio enables generation of 500,000 hours of synthetic speech that reduces ASR error rates by over 30% on Whisper-large-v3.
-
MM-MovieDubber: Towards Multi-Modal Learning for Multi-Modal Movie Dubbing
A movie dubbing system that uses a vision-language model to extract scene type and speaker attributes from silent video, then feeds those attributes as extra conditions into a diffusion-based speech generator, support...
Discussion (0). Sign in to comment.