In this paper, we explore the use of attention-based models for online speech recognition without the usage of language models or searching. Our model is based on an attention-based neural network which directly emits English/Mandarin characters as outputs. The model jointly learns the pronunciation, acoustic and language model. We evaluate the model for online speech recognition on English and...

In light of the studies that investigate when and how English-speaking young children exhibit adult-like abstraction of syntax, this study explores these issues by examining Mandarin-speaking preschoolers ranging from 2to 5-year-olds’ comprehension of the Mandarin SVO-, ba-, long-passive, and short-passive constructions using the forced-choice pointing paradigm. The results indicated that at th...

Noisy listening conditions remain challenging for most cochlear implant patients. The present study simulated the effects of decay rates of excitation spread in cochlear implants on the intelligibility of Mandarin speech in noise. Mandarin sentence and tone stimuli were processed by noise-vocoder, and presented to normal-hearing listeners for identification. The decay rates of excitation spread...

This is a preliminary study examining the tonal production of L1 Taiwanese Southern Min (TSM) speakers who are also fluent in Mandarin. Both languages have tone sandhi rules in which certain lexical tones are neutralized in non-XP-final positions. Disyllabic Mandarin and TSM words with different tonal combinations in frame sentences were examined. The results suggest that Mandarin Tone 1, Tone ...

This study investigated the intelligibility of native and Mandarin-accented English speech for native English and native Mandarin listeners. The word-final voicing contrast was considered (as in minimal pairs such as `cub' and `cup') in a forced-choice word identification task. For these particular talkers and listeners, there was evidence of an interlanguage speech intelligibility benefit for ...

This study investigates the effect of L2-English experience on the perception of the English tense-lax high vowel contrast. Experienced L1-Mandarin, inexperienced L1-Mandarin and L1-English listeners identified and discriminated synthetic heed-hid and who’d-hood continua varying in five steps of F1, F2, and F3 variations and seven steps of duration variations. The results show a strong reliance...

The present study examined the number-specific parental language input to Mandarin- and English-speaking preschool-aged children. Mandarin and English transcripts from the CHILDES database were examined for amount of numeric speech, specific types of numeric speech and syntactic frames in which numeric speech appeared. The results showed that Mandarin-speaking parents talked about number more f...

Most contemporary linguists adopt a sixover nine-tone system in Cantonese. This study confirmed the psychological validity of the sixtone system through Cantonese speakers’ knowledge of Mandarin tone pronunciations using a Mandarin pinyin transcription task. There are pronunciation relationships between Cantonese and Mandarin at the lexical level and previous studies have shown that Cantonese s...

This study looks at whether Taiwan Mandarin speakers were able to detect discourse boundary cues in Mandarin (Guoyu and Putonghua), English, and Japanese. Results showed that there was a distinct language effect. Mandarin boundaries were harder to detect than English and Japanese boundaries for these listeners. This is thought to be due to the different boundary cue compositions in the four lan...