|
TrueSpeech Overview
DSP Group's TrueSpeech is a family of high quality, low bit rate, speech compression algorithms which compress speech down to as little as 1/40th its original size! Several different versions of TrueSpeech at different compression rates are available for licensing, from 8.5 Kbps through 3.9 Kbps. All offer excellent communications over a 14.4 Kbps or better modem.
TrueSpeech 8.5 is the 8.5 Kbps member of DSP Group's TrueSpeech family of software products. It is a low complexity speech coder, which is an integral component of Microsoft windows and has also been endorsed by Dialogic for computer telephony products. TrueSpeech 8.5 should be used when compatibility with Microsoft is a prerequisite.
Speech information can now be exchanged compatibly between different applications. For example, using TrueSpeech 8.5 for digital simultaneous voice and data applications (DSVD), it may be feasible to utilize the same DSP chip for both speech compression and high speed modem data pump tasks. At the sampling rate of 8 KHz, continuous digital speech is compressed from 128 Kbps to 8.5 Kbps, a 15:1 compression ratio, while maintaining good speech quality. With slightly lower voice quality and lower levels of compression, TrueSpeech 8.5 requires only about half the MIPS and program memory space as TrueSpeech 6.3 and 5.3.
The following summary compares the TrueSpeech 8.5, 6.3, 5.3, 4.8 and 4.1 Kbps algorithms:
|
COMPRESSION / PROGRAM** |
|
TrueSpeech |
Quality |
Ratio |
MIPS* |
ROM |
RAM |
|
8.5 |
Good |
15:1 |
9-9.5 |
4-6.5k |
1-2k |
|
6.3 |
Very Good |
20:1 |
20-28 |
16k** |
2.2K** |
|
5.3 |
good |
24:1 |
20-28 |
16k** |
2.2k** |
|
4.8 |
fair |
26:1 |
20-28 |
16k** |
2.2k** |
|
4.1 |
fair |
30:1 |
20-28 |
16k** |
2.2k** |
|
*16 bit fixed point DSP, combined encoder/decoder
* 16 bit fixed point DSP, combined encoder/decoder
** Estimates based on Motorola 56156
Listen to TrueSpeech samples
For licensing information please contact our TrueSpeech licensing manager at TrueSpeech@dsp.co.il
T R U E S P E E C H ®
Giving Windows a Voice
When Microsoft went shopping for a technology to offer users of the Windows operating system efficient access to compatible, quality speech technology, it decided on using TrueSpeech from DSP Group of Santa Clara, California. End users need--and are asking for--compatible, quality speech for multimedia applications on their PCs and other personal communication devices. DSP Group is an industry leader in developing and marketing speech and digital signal processor technologies for the PC, multimedia, communications and consumer markets. Microsoft chose TrueSpeech because of its combination of high voice quality and efficient, digital representation of speech.
Currently, TrueSpeech audio files can be created from standard WAV files by using the Sound Recorder for Windows 95 and Windows NT, and can also be played using the Windows Media Player.
How to Use the Sound Recorder to convert from WAV to TrueSpeech formatted files:
In Sound Recorder:
- Select Open from the File menu. Select the desired WAV file, and click OK.
- Select Save As from the File menu.
- Click Change to display the Sound Selection dialog box
- Select DSP Group TrueSpeech(TM) from the Format list box, and click OK.
- Specify a new Filename, if desired, and click OK.
The new file is encoded in the TrueSpeech format with a compression rate of 15x.
|
Truespeech® Licensing
