Results 181 to 190 of about 14,590,374 (240)
Some of the next articles are maybe not open access.
BASE TTS: Lessons from building a billion-parameter Text-to-Speech model on 100K hours of data
arXiv.orgWe introduce a text-to-speech (TTS) model called BASE TTS, which stands for $\textbf{B}$ig $\textbf{A}$daptive $\textbf{S}$treamable TTS with $\textbf{E}$mergent abilities. BASE TTS is the largest TTS model to-date, trained on 100K hours of public domain
Mateusz Lajszczak +18 more
semanticscholar +1 more source
1996
1. List of contributors 2. Abbreviations used in the glosses 3. Introductory remarks on reported speech and thought (by Janssen, Theo) 4. 1. Slavic languages 5. Shifting points of orientation in Modern Russian: Tense selection in 'reported perception' (by Barentsen, Adriaan) 6. Reported speech in South Slavic (by Gvozdanovic, Jadranka) 7. 2.
openaire +1 more source
1. List of contributors 2. Abbreviations used in the glosses 3. Introductory remarks on reported speech and thought (by Janssen, Theo) 4. 1. Slavic languages 5. Shifting points of orientation in Modern Russian: Tense selection in 'reported perception' (by Barentsen, Adriaan) 6. Reported speech in South Slavic (by Gvozdanovic, Jadranka) 7. 2.
openaire +1 more source
The SAGE Encyclopedia of Human Communication Sciences and Disorders, 2019
We explore unsupervised pre-training for speech recognition by learning representations of raw audio. wav2vec is trained on large amounts of unlabeled audio data and the resulting representations are then used to improve acoustic model training.
Steffen Schneider +3 more
semanticscholar +1 more source
We explore unsupervised pre-training for speech recognition by learning representations of raw audio. wav2vec is trained on large amounts of unlabeled audio data and the resulting representations are then used to improve acoustic model training.
Steffen Schneider +3 more
semanticscholar +1 more source
The Impoliteness of Slurs and Other Pejoratives in Reported Speech
, 2020Maria Paola Tenchini, Aldo Frigerio
semanticscholar +1 more source
Philosophical Studies, 2018
Indirect speech reports can be true even if they attribute to the speaker the saying of something weaker than what she in fact expressed, yet not all weakenings of what the speaker expressed yield true reports. For example, if Anna utters ‘Bob and Carla passed the exam’, we can accurately report her as having said that Carla passed the exam, but we can
openaire +1 more source
Indirect speech reports can be true even if they attribute to the speaker the saying of something weaker than what she in fact expressed, yet not all weakenings of what the speaker expressed yield true reports. For example, if Anna utters ‘Bob and Carla passed the exam’, we can accurately report her as having said that Carla passed the exam, but we can
openaire +1 more source
1987
A news report on some event will normally consist of two things: descriptions of events—what has happened, is happening, or may happen—and descriptions of talk—what people have said (or, sometimes, what people haven’t said) in connection with what has happened, is happening, or may happen. Very commonly, especially in political reporting, what has been
openaire +1 more source
A news report on some event will normally consist of two things: descriptions of events—what has happened, is happening, or may happen—and descriptions of talk—what people have said (or, sometimes, what people haven’t said) in connection with what has happened, is happening, or may happen. Very commonly, especially in political reporting, what has been
openaire +1 more source
Вопросы языкознания / Voprosy Jazykoznanija
The paper explores reported speech in Bezhta (< Nakh-Daghestanian). Bezhta reported speech typically consists of 1) a framing clause involving a verb of speech and 2) a quotation clause followed by a quotative particle. Other reporting strategies include presenting the reported speech either by simply juxtaposing the framing clause and the ...
openaire +1 more source
The paper explores reported speech in Bezhta (< Nakh-Daghestanian). Bezhta reported speech typically consists of 1) a framing clause involving a verb of speech and 2) a quotation clause followed by a quotative particle. Other reporting strategies include presenting the reported speech either by simply juxtaposing the framing clause and the ...
openaire +1 more source
Identifying Media Bias by Analyzing Reported Speech
Industrial Conference on Data Mining, 2017Konstantina Lazaridou +2 more
semanticscholar +1 more source