This paper provides an evaluation and design framework for comparing representation-model pairs and shows that RVQ's residual order gives ordered capacity but not ordered semantics, and that AudioLM's semantic-versus-acoustic cascade is one explicit placement of this boundary rather than a universal template.
Abstract
Every audio generative system makes two coupled decisions: what representation to generate, and how to model its distribution. This paper organizes audio generative modeling around this coupling. For representation design, we compare discrete, continuous, and hybrid latents through four objectives: representation burden, distortion, empirical modelability, and streaming compatibility. For distribution modeling, rather than treating a latent's difficulty as an intrinsic scalar, we use two diagnostic dimensions: dependency horizon, how far useful context extends, and conditional ambiguity, how much uncertainty remains after conditioning. These dimensions refine the common semantic-versus-acoustic intuition: variables with a long dependency horizon should receive global modeling capacity. Conditionally ambiguous detail may be delegated to a local or iterative generator. Applied to representative systems, this view shows that RVQ's residual order gives ordered capacity but not ordered semantics, that AudioLM's semantic-versus-acoustic cascade is one explicit placement of this boundary rather than a universal template, and that autoregression, iterative refinement, and hybrid designs differ chiefly in how they trade dependency horizon against critical-path generation cost. The distinction between discrete and continuous latents describes the output interface; dependency horizon, conditional ambiguity, and streaming determine how that interface should be modeled. Rather than cataloguing individual systems, we provide an evaluation and design framework for comparing representation-model pairs.
This framework produces both a transformation embedding and a processed-audio embedding, and it finds that the two play complementary roles: distance-based tasks favor the former, while probe-based tasks favor the latter.
Sungho Lee, Marco A. Mart'inez-Ram'irez, Junghyun Koo et al.· 0 citations
AURORA-LM is introduced, a continuous-latent diffusion language model that separates the construction of a decodable text representation from the modeling of its distribution, and achieves the strongest performance among evaluated continuous and diffusion-based language models on OpenWebText free generation and XSum summarization.
Jiajun Liang, Yu-Ling Liao, Yukang Cao et al.· 1 citation
Text-to-speech systems often face a trade-off between natural prosody and efficient inference: higher perceptual quality typically comes at increased computational cost and latency. We present TontaubeV1, a model that preserves natural prosody while enabling streaming from a single consumer GPU. Speech is encoded by the hierarchical DualCodec representation at 12.5 Hz, which separates a semantic stream from successive acoustic refinements. Our design assumes that prosodic structure is largely established when the semantic stream is generated, and allocates capacity accordingly: a Qwen3-1.7B-derived transformer predicts that stream and thereby the utterance duration, while three progressively smaller Qwen3-0.6B-derived transformers each add one acoustic refinement. Text is tokenized per character rather than by subword. Paired text and audio markers at shared positions support long-form generation with bounded context, and overlapping DualCodec reconstructions are mapped into the VibeVoice acoustic latent space and decoded causally, enabling streaming despite DualCodec's noncausal decoder. The model accepts up to one minute of reference audio for voice conditioning and is designed primarily for English and German, with additional multilingual support. The four predictors total 2.9B parameters; on a single RTX 5090 the streaming path reaches approximately 200 ms to first audio. In separate non-streaming measurements, the end-to-end real-time factor (RTF) is 0.08 for one input and the aggregate RTF is 0.02 across eight concurrent inputs. On our LLM-as-a-judge audiobook-reading benchmark, TontaubeV1 matches ElevenLabs Flash v2.5 and outperforms Fish Audio S2 Pro, the April 2026 Gradium API, and Cartesia Sonic 3 on prosody. The model weights are released on Hugging Face under the Tontaube Community Model License 1.0.
FullDiT is introduced, a conditional DiT that fuses eight frame-aligned RVQ streams with independently encoded captions and lyrics and uses non-causal self-attention over the complete acoustic latent sequence and outperforms five commercial systems on 15 of 18 automatic metrics.
Yun-Jia Li, Meng-Li Wu, Jun-Yu Dai et al.· 0 citations
FireRedAudio is introduced, a general-purpose audio language model with a shared 9B-parameter LLM that achieves competitive or leading performance in audio understanding and multilingual ASR, strong content accuracy and speaker preservation in zero-shot TTS, leading instruction following in Instruct TTS, and substantial improvements over Ming-UniAudio-Edit in both semantic and acoustic speech editing.
Junjie Li, Xuelong Geng, Kun Xie et al.· 2 citations· ⚡1
Dominant audio classification pipelines rely either on compact handcrafted summaries or on fixed time-frequency frontends such as log-mel representations prior to deep modeling. While highly successful, these representations do not explicitly expose the physical dynamics of the underlying sound-generating event. We introduce MADS (Multi-view Acoustic Descriptor Set), a compact 19-dimensional physics-informed descriptor set de- signed to capture complementary spectral, temporal, mechanical, and stochastic structure in audio signals. Rather than treating sound only as a spectral pattern, MADS encodes properties related to excitation, damping, periodicity, impulsiveness, and structural consistency within a unified multi-view representation. We evaluate MADS using standard classical machine learning models on ESC-10, ESC-50, and MSoS, and compare it against two conventional handcrafted baselines: a compact 26D MFCC- based baseline and an expanded 38D spectral-summary baseline. Across ESC-10 and ESC-50, MADS achieves the strongest peak results overall, reaching 81.00% and 52.78%, respectively, while using roughly half the dimensionality of the 38D baseline. On MSoS, MADS again delivers the strongest top-end performance, reaching 67.48%. These results establish MADS not merely as a competitive standalone descriptor set, but as the foundational descriptor layer of a broader acoustically grounded representation program for future frame-level and deep-learning-compatible audio modeling.
Utsab Ghosh, Roshni Chakraborty· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
