The paper presents two optimizations for forced alignment of audio to text using the Viterbi algorithm. The first optimization applies the Hirschberg algorithm to reduce memory usage from 140 GB to 5 MB for three‑hour inputs and speeds up alignment to one‑third the time of torchaudio on a CPU. The second optimization models alignment as a constrained random walk, enabling pruning that yields an additional 2× speedup on inputs longer than 20 minutes while maintaining over 98 % alignment accuracy.
arXiv:2511. 20973v2 Announce Type: replace-cross Abstract: Large Audio Language Models (LALMs) deliver strong performance across speech and audio tasks, but their audio encoders generate high-rate token sequences (e.
arXiv:2609.18516v1 Announce Type: new Abstract: While Large Language Models excel in natural language processing, efficiently extending their capabilities to spoken input remains a significant challe...
arXiv:2607. 06831v1 Announce Type: cross Abstract: Speech-to-text alignment means finding the temporal boundaries of each word in the audio.
While Large Language Models excel in natural language processing, efficiently extending their capabilities to spoken input remains a significant challenge. Existing methods for building SpeechLLMs oft...
arXiv:2603. 05121v2 Announce Type: replace-cross Abstract: Speech Large Language Models route speech encoder representations into an LLM decoder that typically accounts for over 90% of total parameters.
arXiv:2607. 21332v1 Announce Type: cross Abstract: Phonetic forced alignment is a key technique in phonetic research, yet existing alignment systems lack specialized models for low-resource language varieties.
arXiv:2608. 08569v1 Announce Type: new Abstract: Recent advancements in Speech Large Language Models have demonstrated remarkable capabilities in understanding complex audio tasks.
Phonetic forced alignment is a key technique in phonetic research, yet existing alignment systems lack specialized models for low-resource language varieties. We address this by training text-dependent and text-independent aligners for Chengdu Mandarin using a 17-hour corpus and a custom G2P dictionary.
arXiv:2602.19574v2 Announce Type: replace-cross Abstract: Large-language-model (LLM)-based text-to-speech (TTS) systems can generate natural speech, but most are not designed for low-latency dual-str...
arXiv:2605. 06582v2 Announce Type: replace Abstract: Many operations on sensory data -- comparison, memory, retrieval, and reasoning -- are naturally expressed over discrete symbolic structures.
arXiv:2605. 22083v2 Announce Type: replace-cross Abstract: While flow-matching text-to-speech (TTS) achieves strong zero-shot speaker similarity and naturalness, it remains susceptible to content fidelity issues, particularly skip and repeat errors from imperfect alignment.
arXiv:2605.06582v4 Announce Type: replace Abstract: Modern learning systems represent perceptual signals with continuous vectors, but comparison, retrieval, memory, alignment, and reasoning are often...