Search Results - "Lou, Paria Jamshid"

ShEMO: a large-scale validated database for Persian speech emotion detection by Nezami, Omid Mohamad, Lou, Paria Jamshid, Karami, Mansoureh

“…This paper introduces a large-scale, validated database for Persian called Sharif Emotional Speech Database (ShEMO). The database includes 3000 seminatural…”
Get full text

End-to-End Speech Recognition and Disfluency Removal by Lou, Paria Jamshid, Johnson, Mark

“…Disfluency detection is usually an intermediate step between an automatic speech recognition (ASR) system and a downstream task. By contrast, this paper aims…”
Get full text

Improving Disfluency Detection by Self-Training a Self-Attentive Model by Lou, Paria Jamshid, Johnson, Mark

“…Self-attentive neural syntactic parsers using contextualized word embeddings (e.g. ELMo or BERT) currently produce state-of-the-art results in joint parsing…”
Get full text

Disfluency Detection using a Noisy Channel Model and a Deep Neural Language Model by Lou, Paria Jamshid, Johnson, Mark

“…This paper presents a model for disfluency detection in spontaneous speech transcripts called LSTM Noisy Channel Model. The model uses a Noisy Channel Model…”
Get full text

Neural Constituency Parsing of Speech Transcripts by Lou, Paria Jamshid, Wang, Yufei, Johnson, Mark

“…This paper studies the performance of a neural self-attentive parser on transcribed speech. Speech presents parsing challenges that do not appear in written…”
Get full text

Disfluency Detection using Auto-Correlational Neural Networks by Lou, Paria Jamshid, Anderson, Peter, Johnson, Mark

“…In recent years, the natural language processing community has moved away from task-specific feature engineering, i.e., researchers discovering ad-hoc feature…”
Get full text

ShEMO -- A Large-Scale Validated Database for Persian Speech Emotion Detection by Nezami, Omid Mohamad, Lou, Paria Jamshid, Karami, Mansoureh

“…This paper introduces a large-scale, validated database for Persian called Sharif Emotional Speech Database (ShEMO). The database includes 3000 semi-natural…”
Get full text