arXiv Machine Learning June 11, 2026 By Leonor Barreiros, Raul Monteiro, Afonso Mendes, Gon\c{c}alo M. Correia

Massive Open-Vocabulary Keyword Spotting

Read the original on arXiv Machine Learning →

arXiv:2606. 11279v1 Announce Type: cross Abstract: Automatic speech recognition systems have been shown to under-perform when it comes to transcribing words rarely seen in the training data, namely specialized terminology.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Hugging Face Trending Papers

Sep 14

Typhoon ASR Streaming: Steerable Low-Latency Thai Speech Recognition with Real-Time Shallow Fusion

Open Thai automatic speech recognition (ASR) is dominated by offline, Whisper-based models that read the whole utterance before transcribing, ruling out low-latency uses such as live captioning and vo...

llms agents multimodal benchmarks

arXiv Computation and Language

Sep 15

Typhoon ASR Streaming: Steerable Low-Latency Thai Speech Recognition with Real-Time Shallow Fusion

arXiv:2609.14991v1 Announce Type: new Abstract: Open Thai automatic speech recognition (ASR) is dominated by offline, Whisper-based models that read the whole utterance before transcribing, ruling ou...

By Warit Sirichotedumrong, Tanawin Samutsin, Shah Faisal Wani, Sittipong Sripaisarnmongkol, Kunat Pipatanakul

llms agents multimodal benchmarks

arXiv AI

Aug 24

TurboBias 2.0: Streaming Context-Biasing for Production-Efficient ASR Systems

arXiv:2608.21343v1 Announce Type: cross Abstract: Contextualization is essential for production automatic speech recognition (ASR) systems, where user-provided phrases must be recognized accurately u...

By Vladimir Bataev, Lilit Grigoryan, Andrei Andrusenko, Nikolay Karpov, Vitaly Lavrukhin, Boris Ginsburg

efficiency multimodal

arXiv Computation and Language

Sep 18

Dictionary-Constrained Grapheme-to-Phoneme for Unsegmented Languages from LLM-Annotated Data

The paper introduces a context‑aware neural grapheme‑to‑phoneme (G2P) system for unsegmented languages like Japanese, using a discriminative conditional random field over a word lattice built from dictionaries. It addresses data scarcity by generating over two million sentences with large language models. Experiments show the method surpasses traditional morphological analyzers and neural sequence models, achieving 99.62% target word reading accuracy and very low phoneme error rates on the Joyo‑Kanji‑Yomi benchmark.

By Rui Hu, Zhenpeng Zhan, Xiaolong Lin

llms computer-vision multimodal benchmarks

arXiv Computation and Language

Oct 15

ELARSpeech: A 30K-Hour Dataset Across 675 Underrepresented Languages for Long-Tail Multilingual Speech Technologies

arXiv:2610.19388v1 Announce Type: new Abstract: Massively multilingual speech modeling has made remarkable progress in recent years, yet existing training resources and benchmarks still underrepresen...

By Sangmin Lee, Yejin Jeon, David Ifeoluwa Adelani

multimodal benchmarks

arXiv AI

Sep 30

BaLEEN: Biasing with Latent Encoded Entities for Context-Aware ASR

arXiv:2609.36913v1 Announce Type: cross Abstract: Transcribing domain-specific entities and rare proper nouns remains a major challenge in automatic speech recognition (ASR). In this paper, we propos...

By Chihiro Taguchi, Yotaro Kubo, Rujikorn Charakorn

llms fine-tuning multimodal safety

One email a morning, machine-written

Related stories

Typhoon ASR Streaming: Steerable Low-Latency Thai Speech Recognition with Real-Time Shallow Fusion

Typhoon ASR Streaming: Steerable Low-Latency Thai Speech Recognition with Real-Time Shallow Fusion

TurboBias 2.0: Streaming Context-Biasing for Production-Efficient ASR Systems

Dictionary-Constrained Grapheme-to-Phoneme for Unsegmented Languages from LLM-Annotated Data

ELARSpeech: A 30K-Hour Dataset Across 675 Underrepresented Languages for Long-Tail Multilingual Speech Technologies

BaLEEN: Biasing with Latent Encoded Entities for Context-Aware ASR