All Datasets

Search our off-the-shelf datasets.

Filter by
Category
Category
Mandarin Chinese Duplex Dialogue Corpus (Desktop)
This dataset contains topics such as casual conversations / business meetings (home, workplace, weekly meetings, regular meetings)
Mandarin Chinese Speech Recognition Corpus – ITN Training Set (Mobile)
American English ASR Model Evaluation Report
In this report, we will evaluate the performance of the 6 most representative PA engines, focusing on the result of accuracy, fluency, and prosody in utterance level, accuracy in word level, and accuracy in phoneme level, which are critical and commonly recognized parameters for measuring. For the following content of this report, we will first introduce the 6 engines evaluated and the features we use. Later, we will describe the data we prepared for this experiment. Next, we will illustrate the methodology and evaluation metrics used for the pronunciation assessment. Moreover, we will present the evaluation results and the analysis based on each aspect. Last but not least, this report ends with a conclusion and further discussion.
German TTS Model Evaluation Report
This report evaluates the performance of leading commercial text-to-speech (TTS) systems, focusing on their German audio synthesis capabilities. There are four sections in the report. Section one provides a brief introduction. In section two, we illustrate the methodology and evaluation metrics used for the Functional Metrics Evaluation and Mean Opinion Score (MOS) Evaluation. Sections three present the evaluation results and analysis. The report concludes with a discussion in section four.
French TTS Model Evaluation Report
This report evaluates the performance of leading commercial text-to-speech (TTS) systems, focusing on their France French audio synthesis capabilities. There are four sections in the report. Section one provides a brief introduction. In section two, we illustrate the methodology and evaluation metrics used for the Functional Metrics Evaluation and Mean Opinion Score (MOS) Evaluation. Sections three present the evaluation results and analysis. The report concludes with a discussion in section four.
Italian TTS Model Evaluation Report
This report evaluates the performance of leading commercial text-to-speech (TTS) systems, focusing on their Italian audio synthesis capabilities. There are four sections in the report. Section one provides a brief introduction. In section two, we illustrate the methodology and evaluation metrics used for the Functional Metrics Evaluation and Mean Opinion Score (MOS) Evaluation. Sections three present the evaluation results and analysis. The report concludes with a discussion in section four.
Spanish TTS Model Evaluation Report
This report evaluates the performance of leading commercial text-to-speech (TTS) systems, focusing on their Spain Spanish audio synthesis capabilities. There are four sections in the report. Section one provides a brief introduction. In section two, we illustrate the methodology and evaluation metrics used for the Functional Metrics Evaluation and Mean Opinion Score (MOS) Evaluation. Sections three present the evaluation results and analysis. The report concludes with a discussion in section four.
British English TTS Model Evaluation Report
This report evaluates the performance of leading commercial text-to-speech (TTS) systems, focusing on their British English audio synthesis capabilities. There are four sections in the report. Section one provides a brief introduction. In section two, we illustrate the methodology and evaluation metrics used for the Functional Metrics Evaluation and Mean Opinion Score (MOS) Evaluation. Sections three present the evaluation results and analysis. The report concludes with a discussion in section four.
Hindi TTS Model Evaluation Report
This report evaluates the performance of leading commercial text-to-speech (TTS) systems, focusing on their Hindi audio synthesis capabilities. There are four sections in the report. Section one provides a brief introduction. In section two, we illustrate the methodology and evaluation metrics used for the Functional Metrics Evaluation and Mean Opinion Score (MOS) Evaluation. Sections three present the evaluation results and analysis. The report concludes with a discussion in section four.

Join our newsletter to stay updated

Thank you for signing up!

Stay informed and ahead with the latest updates, insights, and exclusive content delivered straight to your inbox.

By subscribing you agree to with our Privacy Policy and provide consent to receive updates from our company.

Filter by
Category
Category