English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

We propose a unified framework for low resource automatic speech recognitiontasks named meta audio concatenation (MAC). It is easy to implement and can becarried out in extremely low resource environments. Mathematically, we give aclear description of MAC framework from the perspective of bayesian sampling.In this framework, we leverage a novel concatenative synthesis text-to-speechsystem to boost the low resource ASR task. By the concatenative synthesistext-to-speech system, we can integrate language pronunciation rules and adjustthe TTS process. Furthermore, we propose a broad notion of meta audio set tomeet the modeling needs of different languages and different scenes when usingthe system. Extensive experiments have demonstrated the great effectiveness ofMAC on low resource ASR tasks. For CTC greedy search, CTC prefix, attention,and attention rescoring decode mode in Cantonese ASR task, Taiwanese ASR task,and Japanese ASR task the MAC method can reduce the CER by more than 15\%.Furthermore, in the ASR task, MAC beats wav2vec2 (with fine-tuning) on commonvoice datasets of Cantonese and gets really competitive results on common voicedatasets of Taiwanese and Japanese. Among them, it is worth mentioning that weachieve a \textbf{10.9\%} character error rate (CER) on the common voiceCantonese ASR task, bringing about \textbf{30\%} relative improvement comparedto the wav2vec2 (with fine-tuning).

MAC: A unified framework boosting low resource automatic speech recognition