Application Helpers

Chant Application Helpers

Chant Application Helpers provide ready-to-use capabilities for fast application integration. They are designed to yield specific results with minimal application coding requirements.

Chant Developer Workbench 2023 includes the following application helpers:

• Audio Search for finding the time offsets for specific words, phrases, and subphrases in audio recordings;
• Speech Manager for creating and scheduling speech recognition transcription and speech synthesis requests; and
• Talk&Listen for simple invocation of speech synthesis and speech recognition.

Some applications do not require access to the extensive features offered by speech technology SDKs and Chant product class libraries. Application Helpers offer a way to leverage specific capabilities without having to master the low-level details of SDKs or implement complex application architectures. Powerful new capabilities can be integrated in many cases with only one new line of code.

Chant Application Helpers are licensed as part of Chant Developer Workbench.

Audio Search

Chant Audio Search enables applications to find the time offsets for specific words, phrases, and subphrases in audio recordings.

There are two types of audio searches supported: transcription and word spotting.

With transcription searches, an audio recording is transcribed first. Then one or more searches may be performed with simple string or Regular Expression pattern search terms. Matches are returned as offsets in seconds.

With word spotting searches, the audio is word spotted with a list of keywords (i.e., single words or phrases) first. Then one or more searches may be performed to match a keyword originally used in the word spotting. Matches are returned as offsets in seconds.

Audio Search class libraries are available for C++, C++Builder, Delphi, Java (JDK 1.8, 11, 13, 14, 15, 16, 17, 18, 19), C#, and VB .NET (4.5+, 3.1, 5.0, 6.0, 7.0) Windows applications. Integration is simple and fast because a single line of code performs the search and returns offsets in the audio recording if found.

Speech Manager

Chant Speech Manager enables applications to easily create and schedule speech processing requests. A request can specify as much or as little as needed. For example, a request can specify a speech API, engine, language, or allow Speech Manager to select based on availability.

There are two types of speech requests supported: transcription and speech synthesis.

With transcription requests, audio streams (i.e., buffers and files) serve as audio source for speech recognition.

With synthesis requests, audio is generated from synthesizing speech from text and returned as buffers, file, or streamed for live playback.

Requests are created, scheduled, and destroyed. A request is created with optional parameters that specify the details for transcription or synthesis. Once a request is created, it can be managed with various priorities.

Speech Manager class libraries are available for C++, C++Builder, Delphi, Java (JDK 1.8, 11, 13, 14, 15, 16, 17, 18, 19), C#, and VB .NET (4.5+, 3.1, 5.0, 6.0, 7.0) Windows applications. Integration is simple and fast because three lines of code can create, schedule, and destroy a speech processing request.

Talk&Listen

Chant Talk&Listen enables applications to synthesize and recognize speech.

Sometimes applications need a simple way to synthesize and recognize. Chant Talk&Listen application helper enables applications to synthesize and recognize speech without having to worry about events, properties, and callback handlers.

Talk&Listen class libraries are available for C++, C++Builder, Delphi, Java (JDK 1.8, 11, 13, 14, 15, 16, 17, 18, 19), C#, and VB .NET (4.5+, 3.1, 5.0, 6.0, 7.0) Windows applications. Integration is simple and fast because a single line of code can request synthesized speech or request and return recognized speech.